Qwen2-0.5B-Instruct-ru-lora

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: Qwen/Qwen2-0.5B-Instruct
+datasets:
+- generator
+model-index:
+- name: qwen2
+  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. -->
+
+# qwen2
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3740
+
+## 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: 0.0003
+- 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
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-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": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_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 sha256:47b4e4440d86e928350cc61daa30bec5d98deec2324955ca30c079e8323f9677
+size 17640808

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.3739961385726929,
+    "eval_runtime": 16.6407,
+    "eval_samples": 1506,
+    "eval_samples_per_second": 7.452,
+    "eval_steps_per_second": 1.863,
+    "total_flos": 5010632390737920.0,
+    "train_loss": 1.4269454736503766,
+    "train_runtime": 555.1964,
+    "train_samples_per_second": 2.003,
+    "train_steps_per_second": 0.501
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.3739961385726929,
+    "eval_runtime": 16.6407,
+    "eval_samples": 1506,
+    "eval_samples_per_second": 7.452,
+    "eval_steps_per_second": 1.863
+}

runs/Jun07_16-52-07_7c8c7a5b99aa/events.out.tfevents.1717779205.7c8c7a5b99aa.1602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b5384a3558f9f05d9cc522560bc913db605481ada463b367c8f57d9fe9e370
+size 28678

runs/Jun07_16-52-07_7c8c7a5b99aa/events.out.tfevents.1717783807.7c8c7a5b99aa.1602.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8863c3a842747c7ca5461e6cc34179a9920f3c2fb4f8748728de315397b0b71
+size 359

runs/Jun07_16-52-07_7c8c7a5b99aa/events.out.tfevents.1717784106.7c8c7a5b99aa.1602.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dee48cecb3d14a8dda7280c740fb8ef961a901ffa548eb899295165198f1741
+size 8211

runs/Jun07_16-52-07_7c8c7a5b99aa/events.out.tfevents.1717784686.7c8c7a5b99aa.1602.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80f9b6f4e7c12102378fcc1d5a66b9d00e9c2892a4f9f2b814cfb852bde9edd
+size 359

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 5010632390737920.0,
+    "train_loss": 1.4269454736503766,
+    "train_runtime": 555.1964,
+    "train_samples_per_second": 2.003,
+    "train_steps_per_second": 0.501
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 278,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07194244604316546,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.00010714285714285714,
+      "loss": 1.6164,
+      "step": 20
+    },
+    {
+      "epoch": 0.14388489208633093,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00021428571428571427,
+      "loss": 1.49,
+      "step": 40
+    },
+    {
+      "epoch": 0.2158273381294964,
+      "grad_norm": 0.48046875,
+      "learning_rate": 0.00029975975238935744,
+      "loss": 1.4566,
+      "step": 60
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0002914316168191626,
+      "loss": 1.4481,
+      "step": 80
+    },
+    {
+      "epoch": 0.3597122302158273,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00027184967850358286,
+      "loss": 1.42,
+      "step": 100
+    },
+    {
+      "epoch": 0.4316546762589928,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00024257208459621828,
+      "loss": 1.4013,
+      "step": 120
+    },
+    {
+      "epoch": 0.5035971223021583,
+      "grad_norm": 0.4609375,
+      "learning_rate": 0.0002059284716670463,
+      "loss": 1.424,
+      "step": 140
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.00016483459505463747,
+      "loss": 1.394,
+      "step": 160
+    },
+    {
+      "epoch": 0.6474820143884892,
+      "grad_norm": 0.462890625,
+      "learning_rate": 0.000122560320379142,
+      "loss": 1.3847,
+      "step": 180
+    },
+    {
+      "epoch": 0.7194244604316546,
+      "grad_norm": 0.44140625,
+      "learning_rate": 8.246943827734897e-05,
+      "loss": 1.3983,
+      "step": 200
+    },
+    {
+      "epoch": 0.7913669064748201,
+      "grad_norm": 0.462890625,
+      "learning_rate": 4.7752005465070094e-05,
+      "loss": 1.3804,
+      "step": 220
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.45703125,
+      "learning_rate": 2.117050991693609e-05,
+      "loss": 1.3835,
+      "step": 240
+    },
+    {
+      "epoch": 0.935251798561151,
+      "grad_norm": 0.455078125,
+      "learning_rate": 4.840057959975169e-06,
+      "loss": 1.3881,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "step": 278,
+      "total_flos": 5010632390737920.0,
+      "train_loss": 1.4269454736503766,
+      "train_runtime": 555.1964,
+      "train_samples_per_second": 2.003,
+      "train_steps_per_second": 0.501
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 278,
+  "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": 5010632390737920.0,
+  "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 sha256:4fb191e85724f3f85f77a4252eeb796d3de79160a1b94210a10bf3ff99c38793
+size 5368