Model save

README.md

@@ -0,0 +1,74 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: peft
+license: apache-2.0
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: test_0918_upload_3
+  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. -->
+
+# test_0918_upload_3
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9728
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.1111 | 1    | 2.5265          |
+| No log        | 0.2222 | 2    | 2.4336          |
+| No log        | 0.3333 | 3    | 2.3057          |
+| No log        | 0.4444 | 4    | 2.2072          |
+| No log        | 0.5556 | 5    | 2.1376          |
+| No log        | 0.6667 | 6    | 2.0650          |
+| No log        | 0.7778 | 7    | 2.0119          |
+| No log        | 0.8889 | 8    | 1.9691          |
+| No log        | 1.0    | 9    | 1.9728          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 2.18.0
+- 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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_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 sha256:8d2dd0b9c1d7fc3dc00348676b5562662738f0fabffb89472191457f2d6ab8a3
+size 17640136

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endoftext|>": 151643,
+  "<|eot_id|>": 151646,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.804765224456787,
+    "eval_runtime": 0.0629,
+    "eval_samples_per_second": 31.789,
+    "eval_steps_per_second": 15.894,
+    "total_flos": 91033240862720.0,
+    "train_loss": 2.1809828016493054,
+    "train_runtime": 20.1377,
+    "train_samples_per_second": 0.894,
+    "train_steps_per_second": 0.447
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.804765224456787,
+    "eval_runtime": 0.0629,
+    "eval_samples_per_second": 31.789,
+    "eval_steps_per_second": 15.894
+}

runs/Sep18_15-21-27_dsw-83959-79687bc578-gqp55/events.out.tfevents.1726644108.dsw-83959-79687bc578-gqp55.2469751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f742eeb35560adcef92ef085ecc9403cd9078760cc69aefae9de517cbf0489d
+size 8050

runs/Sep18_15-21-27_dsw-83959-79687bc578-gqp55/events.out.tfevents.1726644152.dsw-83959-79687bc578-gqp55.2469751.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e54050071141643ad080774fae191ca9d1e32738e553a3b8d37e3e59dd9172
+size 354

runs/Sep18_15-27-00_dsw-83959-79687bc578-gqp55/events.out.tfevents.1726644432.dsw-83959-79687bc578-gqp55.2473061.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef8a8bd93bd66676ee6124df2cd088c168e2fc1c0602d25a21780b2b67f5363
+size 8050

runs/Sep18_15-29-21_dsw-83959-79687bc578-gqp55/events.out.tfevents.1726644632.dsw-83959-79687bc578-gqp55.2474228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7b7f635a0ed07adda43f624deac5d44a76bb683b51a0443ce3f22c4dd259de
+size 7997

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "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
+    },
+    "151646": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eot_id|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 91033240862720.0,
+    "train_loss": 2.1809828016493054,
+    "train_runtime": 20.1377,
+    "train_samples_per_second": 0.894,
+    "train_steps_per_second": 0.447
+}

trainer_log.jsonl

@@ -0,0 +1,10 @@
+{"current_steps": 1, "total_steps": 9, "eval_loss": 2.526536226272583, "epoch": 0.1111111111111111, "percentage": 11.11, "elapsed_time": "0:00:00", "remaining_time": "0:00:07"}
+{"current_steps": 2, "total_steps": 9, "eval_loss": 2.433619499206543, "epoch": 0.2222222222222222, "percentage": 22.22, "elapsed_time": "0:00:02", "remaining_time": "0:00:09"}
+{"current_steps": 3, "total_steps": 9, "eval_loss": 2.3056671619415283, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "0:00:04", "remaining_time": "0:00:09"}
+{"current_steps": 4, "total_steps": 9, "eval_loss": 2.2071735858917236, "epoch": 0.4444444444444444, "percentage": 44.44, "elapsed_time": "0:00:06", "remaining_time": "0:00:08"}
+{"current_steps": 5, "total_steps": 9, "eval_loss": 2.137558698654175, "epoch": 0.5555555555555556, "percentage": 55.56, "elapsed_time": "0:00:08", "remaining_time": "0:00:06"}
+{"current_steps": 6, "total_steps": 9, "eval_loss": 2.0649843215942383, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:00:10", "remaining_time": "0:00:05"}
+{"current_steps": 7, "total_steps": 9, "eval_loss": 2.011927604675293, "epoch": 0.7777777777777778, "percentage": 77.78, "elapsed_time": "0:00:11", "remaining_time": "0:00:03"}
+{"current_steps": 8, "total_steps": 9, "eval_loss": 1.9691121578216553, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "0:00:13", "remaining_time": "0:00:01"}
+{"current_steps": 9, "total_steps": 9, "eval_loss": 1.9728047847747803, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:15", "remaining_time": "0:00:00"}
+{"current_steps": 9, "total_steps": 9, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1111111111111111,
+      "eval_loss": 2.2465293407440186,
+      "eval_runtime": 0.0671,
+      "eval_samples_per_second": 29.82,
+      "eval_steps_per_second": 14.91,
+      "step": 1
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 2.2040328979492188,
+      "eval_runtime": 0.0606,
+      "eval_samples_per_second": 33.007,
+      "eval_steps_per_second": 16.504,
+      "step": 2
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 2.1323795318603516,
+      "eval_runtime": 0.096,
+      "eval_samples_per_second": 20.823,
+      "eval_steps_per_second": 10.411,
+      "step": 3
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 2.1022720336914062,
+      "eval_runtime": 0.0809,
+      "eval_samples_per_second": 24.732,
+      "eval_steps_per_second": 12.366,
+      "step": 4
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 2.0100858211517334,
+      "eval_runtime": 0.0733,
+      "eval_samples_per_second": 27.273,
+      "eval_steps_per_second": 13.637,
+      "step": 5
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 1.9271330833435059,
+      "eval_runtime": 0.0642,
+      "eval_samples_per_second": 31.137,
+      "eval_steps_per_second": 15.569,
+      "step": 6
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "eval_loss": 1.8663313388824463,
+      "eval_runtime": 0.0621,
+      "eval_samples_per_second": 32.192,
+      "eval_steps_per_second": 16.096,
+      "step": 7
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 1.8211396932601929,
+      "eval_runtime": 0.0608,
+      "eval_samples_per_second": 32.918,
+      "eval_steps_per_second": 16.459,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.804765224456787,
+      "eval_runtime": 0.0612,
+      "eval_samples_per_second": 32.679,
+      "eval_steps_per_second": 16.34,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "step": 9,
+      "total_flos": 91033240862720.0,
+      "train_loss": 2.1809828016493054,
+      "train_runtime": 20.1377,
+      "train_samples_per_second": 0.894,
+      "train_steps_per_second": 0.447
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 91033240862720.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35adc3f09f1e82e58f5cfe7b47643b1e03f055a66610eace7d84c1320c474d1
+size 5432