Upload folder using huggingface_hub

README.md

@@ -1,32 +1,24 @@
 ---
 library_name: transformers
 license: other
-base_model: hon9kon9ize/CantoneseLLM-7B-sft
+base_model: hon9kon9ize/CantoneseLLM-v1.0
 tags:
 - llama-factory
 - full
 - generated_from_trainer
 model-index:
-- name: CantoneseLLMChat-v1.0
+- name: Qwen2.5-7B-sft
   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. -->
 
-# CantoneseLLMChat-v1.0
+# Qwen2.5-7B-sft
 
-This model is a fine-tuned version of [hon9kon9ize/CantoneseLLM-7B-sft](https://huggingface.co/hon9kon9ize/CantoneseLLM-7B-sft) on the dpo_v1 dataset.
+This model is a fine-tuned version of [hon9kon9ize/CantoneseLLM-v1.0](https://huggingface.co/hon9kon9ize/CantoneseLLM-v1.0) on the sft_v1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3170
-- Rewards/chosen: -0.7307
-- Rewards/rejected: -3.1239
-- Rewards/accuracies: 0.8464
-- Rewards/margins: 2.3931
-- Logps/rejected: -226.0627
-- Logps/chosen: -191.7517
-- Logits/rejected: -1.5777
-- Logits/chosen: -1.5363
+- Loss: 0.9464
 
 ## Model description
 
@@ -45,23 +37,83 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_ratio: 0.3
 - num_epochs: 3.0
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
-|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.0835        | 1.3495 | 500  | 0.3282          | -0.6181        | -2.8043          | 0.8494             | 2.1862          | -222.8677      | -190.6253    | -1.5563         | -1.5215       |
-| 0.1151        | 2.6991 | 1000 | 0.3186          | -0.7277        | -3.1230          | 0.8524             | 2.3953          | -226.0546      | -191.7211    | -1.5777         | -1.5363       |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3332        | 0.0480 | 100  | 1.3140          |
+| 1.2185        | 0.0960 | 200  | 1.2879          |
+| 1.1976        | 0.1439 | 300  | 1.2533          |
+| 1.1627        | 0.1919 | 400  | 1.2169          |
+| 1.178         | 0.2399 | 500  | 1.1766          |
+| 1.133         | 0.2879 | 600  | 1.1296          |
+| 1.0466        | 0.3359 | 700  | 1.0983          |
+| 1.0657        | 0.3839 | 800  | 1.0770          |
+| 1.054         | 0.4318 | 900  | 1.0617          |
+| 1.0744        | 0.4798 | 1000 | 1.0487          |
+| 0.9977        | 0.5278 | 1100 | 1.0383          |
+| 0.9778        | 0.5758 | 1200 | 1.0290          |
+| 1.0187        | 0.6238 | 1300 | 1.0211          |
+| 1.085         | 0.6717 | 1400 | 1.0131          |
+| 0.958         | 0.7197 | 1500 | 1.0072          |
+| 1.0482        | 0.7677 | 1600 | 1.0007          |
+| 0.9447        | 0.8157 | 1700 | 0.9946          |
+| 1.0           | 0.8637 | 1800 | 0.9894          |
+| 0.9685        | 0.9117 | 1900 | 0.9849          |
+| 0.8576        | 0.9596 | 2000 | 0.9807          |
+| 0.8853        | 1.0076 | 2100 | 0.9775          |
+| 0.947         | 1.0556 | 2200 | 0.9739          |
+| 0.9207        | 1.1036 | 2300 | 0.9713          |
+| 0.8596        | 1.1516 | 2400 | 0.9691          |
+| 1.0277        | 1.1995 | 2500 | 0.9655          |
+| 0.9646        | 1.2475 | 2600 | 0.9631          |
+| 0.8583        | 1.2955 | 2700 | 0.9613          |
+| 0.9367        | 1.3435 | 2800 | 0.9589          |
+| 0.9146        | 1.3915 | 2900 | 0.9570          |
+| 0.9697        | 1.4395 | 3000 | 0.9556          |
+| 0.8713        | 1.4874 | 3100 | 0.9542          |
+| 0.9855        | 1.5354 | 3200 | 0.9524          |
+| 0.8651        | 1.5834 | 3300 | 0.9511          |
+| 0.9448        | 1.6314 | 3400 | 0.9495          |
+| 0.8997        | 1.6794 | 3500 | 0.9485          |
+| 1.0446        | 1.7273 | 3600 | 0.9475          |
+| 0.8862        | 1.7753 | 3700 | 0.9465          |
+| 0.873         | 1.8233 | 3800 | 0.9456          |
+| 0.9893        | 1.8713 | 3900 | 0.9448          |
+| 0.8915        | 1.9193 | 4000 | 0.9442          |
+| 0.8854        | 1.9673 | 4100 | 0.9435          |
+| 0.7608        | 2.0152 | 4200 | 0.9447          |
+| 0.796         | 2.0632 | 4300 | 0.9464          |
+| 0.9225        | 2.1112 | 4400 | 0.9467          |
+| 0.9901        | 2.1592 | 4500 | 0.9467          |
+| 0.9263        | 2.2072 | 4600 | 0.9468          |
+| 0.7735        | 2.2551 | 4700 | 0.9467          |
+| 0.8454        | 2.3031 | 4800 | 0.9464          |
+| 0.8562        | 2.3511 | 4900 | 0.9466          |
+| 0.8923        | 2.3991 | 5000 | 0.9464          |
+| 0.7529        | 2.4471 | 5100 | 0.9463          |
+| 0.8421        | 2.4951 | 5200 | 0.9463          |
+| 0.8578        | 2.5430 | 5300 | 0.9463          |
+| 0.8143        | 2.5910 | 5400 | 0.9464          |
+| 0.8117        | 2.6390 | 5500 | 0.9463          |
+| 0.861         | 2.6870 | 5600 | 0.9464          |
+| 0.8415        | 2.7350 | 5700 | 0.9463          |
+| 0.7846        | 2.7829 | 5800 | 0.9463          |
+| 0.7605        | 2.8309 | 5900 | 0.9464          |
+| 0.8721        | 2.8789 | 6000 | 0.9464          |
+| 0.8566        | 2.9269 | 6100 | 0.9464          |
+| 0.7978        | 2.9749 | 6200 | 0.9464          |
 
 
 ### Framework versions

all_results.json

@@ -1,20 +1,12 @@
 {
-    "epoch": 2.9959514170040484,
-    "eval_logits/chosen": -1.5362521409988403,
-    "eval_logits/rejected": -1.577704906463623,
-    "eval_logps/chosen": -191.7516632080078,
-    "eval_logps/rejected": -226.06272888183594,
-    "eval_loss": 0.31698280572891235,
-    "eval_rewards/accuracies": 0.8463855385780334,
-    "eval_rewards/chosen": -0.7307406663894653,
-    "eval_rewards/margins": 2.3931150436401367,
-    "eval_rewards/rejected": -3.1238558292388916,
-    "eval_runtime": 23.3432,
-    "eval_samples_per_second": 14.137,
-    "eval_steps_per_second": 3.556,
-    "total_flos": 4.5615607240812134e+17,
-    "train_loss": 0.26195224279218965,
-    "train_runtime": 3105.2921,
-    "train_samples_per_second": 2.862,
-    "train_steps_per_second": 0.357
+    "epoch": 2.9998200683740177,
+    "eval_loss": 0.9463909864425659,
+    "eval_runtime": 178.4011,
+    "eval_samples_per_second": 41.536,
+    "eval_steps_per_second": 10.387,
+    "total_flos": 6.498465993073754e+18,
+    "train_loss": 0.937529916860168,
+    "train_runtime": 37609.4943,
+    "train_samples_per_second": 5.32,
+    "train_steps_per_second": 0.166
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/pj24001684/ku40000295/jc/models/Qwen2.5-7B-sft",
+  "_name_or_path": "hon9kon9ize/Qwen2.5-7B-cpt",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -27,4 +27,4 @@
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 152064
-}
+}

eval_results.json

@@ -1,15 +1,7 @@
 {
-    "epoch": 2.9959514170040484,
-    "eval_logits/chosen": -1.5362521409988403,
-    "eval_logits/rejected": -1.577704906463623,
-    "eval_logps/chosen": -191.7516632080078,
-    "eval_logps/rejected": -226.06272888183594,
-    "eval_loss": 0.31698280572891235,
-    "eval_rewards/accuracies": 0.8463855385780334,
-    "eval_rewards/chosen": -0.7307406663894653,
-    "eval_rewards/margins": 2.3931150436401367,
-    "eval_rewards/rejected": -3.1238558292388916,
-    "eval_runtime": 23.3432,
-    "eval_samples_per_second": 14.137,
-    "eval_steps_per_second": 3.556
+    "epoch": 2.9998200683740177,
+    "eval_loss": 0.9463909864425659,
+    "eval_runtime": 178.4011,
+    "eval_samples_per_second": 41.536,
+    "eval_steps_per_second": 10.387
 }

generation_config.json

@@ -3,4 +3,4 @@
   "eos_token_id": 151645,
   "max_new_tokens": 2048,
   "transformers_version": "4.45.0"
-}
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67a79228c8074f3a3dfff18c2f21e5f863f95b349a31b6d21a947f4e909c6f26
+oid sha256:6e46f9bcd51417c7fe4f6ee7174df3350c5d054b47cd53eba8c6db80677ff144
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fae4dffdb2d66b9ba2236d298a23e03ab0dc4de179f81bbdec38bce9e37057e
+oid sha256:c22043facd2fb35cd773bf19a3b868e67047e1fe0c907f055864f243649aabf4
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6709fe3e67979ee59a4f19cd0cb471837c09c2b251b88495d2d70f3a233097
+oid sha256:f94ec0aca7510f6196dc05094e5b321d32c5f9fe210f58819a9e5983ee654b88
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13117fa1a4e8e35f74c8c2ce20d2d07397a836866a947029f13c0f683275f2c
+oid sha256:23834907a8855efdec9c5ce5ffbfc1ee56e2fca5fc6a00df562ede4f70a3303a
 size 1089994880

runs/Oct03_20-36-50_c0002/events.out.tfevents.1727955439.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9819779c90e165f2a79e52765391e384b230f029f412d0fe87ad341a55b88888
+size 286095

runs/Oct03_20-36-50_c0002/events.out.tfevents.1727993248.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44cf150d3dc29ca8ffda0c93414ff2031b34ddf883273e9bacbb9ef01042075
+size 311

runs/Sep23_06-10-16_c0002/events.out.tfevents.1727039792.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b718e16bd6facd03ac44048c1ecc3f060195b1b9a02a21d2066b65054b24318
+size 206530

runs/Sep23_06-10-16_c0002/events.out.tfevents.1727057464.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5472c69abe32e2f436290dad5b713cd7715d42c824d12e9ef1078698bdbdb74e
+size 311

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67909bb0045622af428982dee9b3f1033cf5c4bca5c9423a028d3748364ee14f
+size 1044277

tokenizer_config.json

@@ -205,4 +205,4 @@
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
-}
+}

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.9959514170040484,
-    "total_flos": 4.5615607240812134e+17,
-    "train_loss": 0.26195224279218965,
-    "train_runtime": 3105.2921,
-    "train_samples_per_second": 2.862,
-    "train_steps_per_second": 0.357
+    "epoch": 2.9998200683740177,
+    "total_flos": 6.498465993073754e+18,
+    "train_loss": 0.937529916860168,
+    "train_runtime": 37609.4943,
+    "train_samples_per_second": 5.32,
+    "train_steps_per_second": 0.166
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc442c3d32be2bbc2d811b67fd7c92e7801cf862c05b6b1929828c997ece013e
+oid sha256:fe9bca8819b0827758099d317d961fbb64bf0550bb5da2ec6faf00cab3280dbc
 size 5432