backup 02_lr3e-4 pre-cleanup

.gitattributes

@@ -131,3 +131,5 @@ _DRYRUN3/02_single_ar/last/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 01_llada3e-4_qwen3e-4/01_qwen_body/step50-val0.6665/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 02_lr2e-4/02_single_ar/step100-val1.0025/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 02_lr2e-4/02_single_ar/step50-val0.9883/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+02_lr3e-4/02_single_ar/step100-val1.0480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+02_lr3e-4/02_single_ar/step50-val0.9958/tokenizer.json filter=lfs diff=lfs merge=lfs -text

02_lr3e-4/02_single_ar.log

@@ -0,0 +1,243 @@
+trainable params: 269,936,128 || all params: 1,580,276,736 || trainable%: 17.0816
+val set: 500 samples  eval_interval=50  eval_batches=20
+[qwen] step 20/3375 loss=1.4190 lr=6.00e-05 elapsed=16s
+[qwen] step 40/3375 loss=1.0959 lr=1.20e-04 elapsed=29s
+[qwen] step 50 val_loss=0.9958
+/home/jgai/miniconda3/envs/diffar/lib/python3.10/site-packages/peft/utils/save_and_load.py:300: UserWarning: Setting `save_embedding_layers` to `True` as the embedding layer has been resized during finetuning.
+  warnings.warn(
+[topk] +save step=50 val=0.9958 (top-1/2)
+[qwen] step 60/3375 loss=0.9251 lr=1.80e-04 elapsed=47s
+[qwen] step 80/3375 loss=0.8866 lr=2.40e-04 elapsed=60s
+[qwen] step 100/3375 loss=1.2823 lr=3.00e-04 elapsed=73s
+[qwen] step 100 val_loss=1.0480
+[topk] +save step=100 val=1.0480 (top-2/2)
+[qwen] step 120/3375 loss=0.9473 lr=3.00e-04 elapsed=92s
+[qwen] step 140/3375 loss=1.0655 lr=3.00e-04 elapsed=105s
+[qwen] step 150 val_loss=1.1522
+[qwen] step 160/3375 loss=1.0025 lr=3.00e-04 elapsed=122s
+[qwen] step 180/3375 loss=1.1486 lr=3.00e-04 elapsed=135s
+[qwen] step 200/3375 loss=1.2581 lr=2.99e-04 elapsed=148s
+[qwen] step 200 val_loss=1.2077
+[qwen] step 220/3375 loss=1.3794 lr=2.99e-04 elapsed=165s
+[qwen] step 240/3375 loss=1.2407 lr=2.99e-04 elapsed=178s
+[qwen] step 250 val_loss=1.2225
+[qwen] step 260/3375 loss=1.1534 lr=2.98e-04 elapsed=195s
+[qwen] step 280/3375 loss=1.3061 lr=2.98e-04 elapsed=208s
+[qwen] step 300/3375 loss=1.2825 lr=2.97e-04 elapsed=221s
+[qwen] step 300 val_loss=1.2789
+[qwen] step 320/3375 loss=1.6533 lr=2.97e-04 elapsed=238s
+[qwen] step 340/3375 loss=1.3661 lr=2.96e-04 elapsed=251s
+[qwen] step 350 val_loss=1.3316
+[qwen] step 360/3375 loss=1.2988 lr=2.95e-04 elapsed=268s
+[qwen] step 380/3375 loss=1.1333 lr=2.95e-04 elapsed=281s
+[qwen] step 400/3375 loss=1.3218 lr=2.94e-04 elapsed=294s
+[qwen] step 400 val_loss=1.3202
+[qwen] step 420/3375 loss=1.4468 lr=2.93e-04 elapsed=311s
+[qwen] step 440/3375 loss=1.3067 lr=2.92e-04 elapsed=324s
+[qwen] step 450 val_loss=1.3624
+[qwen] step 460/3375 loss=1.2693 lr=2.91e-04 elapsed=341s
+[qwen] step 480/3375 loss=1.6014 lr=2.90e-04 elapsed=354s
+[qwen] step 500/3375 loss=1.4534 lr=2.89e-04 elapsed=367s
+[qwen] step 500 val_loss=1.3989
+[qwen] step 520/3375 loss=1.4428 lr=2.88e-04 elapsed=384s
+[qwen] step 540/3375 loss=1.6002 lr=2.87e-04 elapsed=397s
+[qwen] step 550 val_loss=1.4346
+[qwen] step 560/3375 loss=1.5092 lr=2.86e-04 elapsed=414s
+[qwen] step 580/3375 loss=1.3141 lr=2.84e-04 elapsed=427s
+[qwen] step 600/3375 loss=1.4143 lr=2.83e-04 elapsed=440s
+[qwen] step 600 val_loss=1.4360
+[qwen] step 620/3375 loss=1.4728 lr=2.82e-04 elapsed=457s
+[qwen] step 640/3375 loss=1.3205 lr=2.80e-04 elapsed=470s
+[qwen] step 650 val_loss=1.4618
+[qwen] step 660/3375 loss=1.6431 lr=2.79e-04 elapsed=487s
+[qwen] step 680/3375 loss=1.4271 lr=2.77e-04 elapsed=500s
+[qwen] step 700/3375 loss=1.5265 lr=2.76e-04 elapsed=513s
+[qwen] step 700 val_loss=1.5156
+[qwen] step 720/3375 loss=1.5611 lr=2.74e-04 elapsed=530s
+[qwen] step 740/3375 loss=1.6806 lr=2.73e-04 elapsed=543s
+[qwen] step 750 val_loss=1.5356
+[qwen] step 760/3375 loss=1.6672 lr=2.71e-04 elapsed=560s
+[qwen] step 780/3375 loss=1.7321 lr=2.69e-04 elapsed=573s
+[qwen] step 800/3375 loss=1.7783 lr=2.67e-04 elapsed=586s
+[qwen] step 800 val_loss=1.5288
+[qwen] step 820/3375 loss=1.7235 lr=2.66e-04 elapsed=603s
+[qwen] step 840/3375 loss=1.3468 lr=2.64e-04 elapsed=616s
+[qwen] step 850 val_loss=1.5744
+[qwen] step 860/3375 loss=1.8283 lr=2.62e-04 elapsed=633s
+[qwen] step 880/3375 loss=1.5620 lr=2.60e-04 elapsed=646s
+[qwen] step 900/3375 loss=1.3807 lr=2.58e-04 elapsed=659s
+[qwen] step 900 val_loss=1.6065
+[qwen] step 920/3375 loss=1.7706 lr=2.56e-04 elapsed=676s
+[qwen] step 940/3375 loss=1.6711 lr=2.54e-04 elapsed=689s
+[qwen] step 950 val_loss=1.6265
+[qwen] step 960/3375 loss=1.8286 lr=2.52e-04 elapsed=706s
+[qwen] step 980/3375 loss=1.7251 lr=2.50e-04 elapsed=719s
+[qwen] step 1000/3375 loss=1.7153 lr=2.47e-04 elapsed=732s
+[qwen] step 1000 val_loss=1.6601
+[qwen] step 1020/3375 loss=1.4532 lr=2.45e-04 elapsed=749s
+[qwen] step 1040/3375 loss=1.7801 lr=2.43e-04 elapsed=762s
+[qwen] step 1050 val_loss=1.6369
+[qwen] step 1060/3375 loss=1.7198 lr=2.41e-04 elapsed=779s
+[qwen] step 1080/3375 loss=1.7278 lr=2.38e-04 elapsed=792s
+[qwen] step 1100/3375 loss=1.6943 lr=2.36e-04 elapsed=806s
+[qwen] step 1100 val_loss=1.6594
+[qwen] step 1120/3375 loss=1.7638 lr=2.34e-04 elapsed=822s
+[qwen] step 1140/3375 loss=1.8016 lr=2.31e-04 elapsed=836s
+[qwen] step 1150 val_loss=1.6916
+[qwen] step 1160/3375 loss=1.6980 lr=2.29e-04 elapsed=852s
+[qwen] step 1180/3375 loss=1.8101 lr=2.26e-04 elapsed=865s
+[qwen] step 1200/3375 loss=1.6930 lr=2.24e-04 elapsed=879s
+[qwen] step 1200 val_loss=1.7034
+[qwen] step 1220/3375 loss=1.6966 lr=2.21e-04 elapsed=895s
+[qwen] step 1240/3375 loss=1.9113 lr=2.19e-04 elapsed=909s
+[qwen] step 1250 val_loss=1.7144
+[qwen] step 1260/3375 loss=1.7071 lr=2.16e-04 elapsed=926s
+[qwen] step 1280/3375 loss=1.6978 lr=2.14e-04 elapsed=939s
+[qwen] step 1300/3375 loss=1.5127 lr=2.11e-04 elapsed=952s
+[qwen] step 1300 val_loss=1.7583
+[qwen] step 1320/3375 loss=1.6600 lr=2.08e-04 elapsed=969s
+[qwen] step 1340/3375 loss=1.8258 lr=2.06e-04 elapsed=982s
+[qwen] step 1350 val_loss=1.7675
+[qwen] step 1360/3375 loss=1.7928 lr=2.03e-04 elapsed=999s
+[qwen] step 1380/3375 loss=1.5873 lr=2.00e-04 elapsed=1013s
+[qwen] step 1400/3375 loss=1.9264 lr=1.98e-04 elapsed=1026s
+[qwen] step 1400 val_loss=1.7697
+[qwen] step 1420/3375 loss=2.1952 lr=1.95e-04 elapsed=1043s
+[qwen] step 1440/3375 loss=1.7583 lr=1.92e-04 elapsed=1056s
+[qwen] step 1450 val_loss=1.7605
+[qwen] step 1460/3375 loss=1.7092 lr=1.89e-04 elapsed=1073s
+[qwen] step 1480/3375 loss=1.8627 lr=1.87e-04 elapsed=1086s
+[qwen] step 1500/3375 loss=2.0176 lr=1.84e-04 elapsed=1099s
+[qwen] step 1500 val_loss=1.7695
+[qwen] step 1520/3375 loss=1.8845 lr=1.81e-04 elapsed=1116s
+[qwen] step 1540/3375 loss=1.8960 lr=1.78e-04 elapsed=1129s
+[qwen] step 1550 val_loss=1.7947
+[qwen] step 1560/3375 loss=1.8978 lr=1.75e-04 elapsed=1146s
+[qwen] step 1580/3375 loss=1.9368 lr=1.73e-04 elapsed=1159s
+[qwen] step 1600/3375 loss=1.9132 lr=1.70e-04 elapsed=1172s
+[qwen] step 1600 val_loss=1.8150
+[qwen] step 1620/3375 loss=1.6989 lr=1.67e-04 elapsed=1189s
+[qwen] step 1640/3375 loss=1.5530 lr=1.64e-04 elapsed=1202s
+[qwen] step 1650 val_loss=1.8466
+[qwen] step 1660/3375 loss=1.7681 lr=1.61e-04 elapsed=1219s
+[qwen] step 1680/3375 loss=2.0160 lr=1.58e-04 elapsed=1232s
+[qwen] step 1700/3375 loss=1.5446 lr=1.55e-04 elapsed=1245s
+[qwen] step 1700 val_loss=1.8523
+[qwen] step 1720/3375 loss=1.7760 lr=1.53e-04 elapsed=1262s
+[qwen] step 1740/3375 loss=2.0169 lr=1.50e-04 elapsed=1275s
+[qwen] step 1750 val_loss=1.8309
+[qwen] step 1760/3375 loss=1.7288 lr=1.47e-04 elapsed=1292s
+[qwen] step 1780/3375 loss=2.0372 lr=1.44e-04 elapsed=1305s
+[qwen] step 1800/3375 loss=1.9820 lr=1.41e-04 elapsed=1318s
+[qwen] step 1800 val_loss=1.8484
+[qwen] step 1820/3375 loss=1.7448 lr=1.38e-04 elapsed=1335s
+[qwen] step 1840/3375 loss=1.9355 lr=1.35e-04 elapsed=1348s
+[qwen] step 1850 val_loss=1.8301
+[qwen] step 1860/3375 loss=1.8490 lr=1.32e-04 elapsed=1365s
+[qwen] step 1880/3375 loss=1.7090 lr=1.30e-04 elapsed=1378s
+[qwen] step 1900/3375 loss=1.8764 lr=1.27e-04 elapsed=1391s
+[qwen] step 1900 val_loss=1.8435
+[qwen] step 1920/3375 loss=1.6250 lr=1.24e-04 elapsed=1408s
+[qwen] step 1940/3375 loss=1.7256 lr=1.21e-04 elapsed=1421s
+[qwen] step 1950 val_loss=1.8108
+[qwen] step 1960/3375 loss=1.8322 lr=1.18e-04 elapsed=1438s
+[qwen] step 1980/3375 loss=1.6832 lr=1.15e-04 elapsed=1451s
+[qwen] step 2000/3375 loss=2.0800 lr=1.13e-04 elapsed=1464s
+[qwen] step 2000 val_loss=1.7897
+[qwen] step 2020/3375 loss=1.7012 lr=1.10e-04 elapsed=1481s
+[qwen] step 2040/3375 loss=1.7053 lr=1.07e-04 elapsed=1494s
+[qwen] step 2050 val_loss=1.9752
+[qwen] step 2060/3375 loss=1.8765 lr=1.04e-04 elapsed=1511s
+[qwen] step 2080/3375 loss=1.5653 lr=1.02e-04 elapsed=1524s
+[qwen] step 2100/3375 loss=1.7904 lr=9.89e-05 elapsed=1537s
+[qwen] step 2100 val_loss=1.7718
+[qwen] step 2120/3375 loss=1.5574 lr=9.62e-05 elapsed=1554s
+[qwen] step 2140/3375 loss=1.9045 lr=9.35e-05 elapsed=1567s
+[qwen] step 2150 val_loss=1.7686
+[qwen] step 2160/3375 loss=1.8159 lr=9.09e-05 elapsed=1584s
+[qwen] step 2180/3375 loss=2.0620 lr=8.82e-05 elapsed=1597s
+[qwen] step 2200/3375 loss=1.9263 lr=8.56e-05 elapsed=1610s
+[qwen] step 2200 val_loss=1.7645
+[qwen] step 2220/3375 loss=1.5807 lr=8.30e-05 elapsed=1627s
+[qwen] step 2240/3375 loss=1.9242 lr=8.05e-05 elapsed=1640s
+[qwen] step 2250 val_loss=1.7586
+[qwen] step 2260/3375 loss=1.7694 lr=7.79e-05 elapsed=1657s
+[qwen] step 2280/3375 loss=1.7175 lr=7.54e-05 elapsed=1671s
+[qwen] step 2300/3375 loss=2.1690 lr=7.29e-05 elapsed=1684s
+[qwen] step 2300 val_loss=1.7476
+[qwen] step 2320/3375 loss=1.5911 lr=7.05e-05 elapsed=1701s
+[qwen] step 2340/3375 loss=1.8048 lr=6.81e-05 elapsed=1714s
+[qwen] step 2350 val_loss=1.7460
+[qwen] step 2360/3375 loss=1.5357 lr=6.57e-05 elapsed=1731s
+[qwen] step 2380/3375 loss=1.6896 lr=6.33e-05 elapsed=1744s
+[qwen] step 2400/3375 loss=1.7887 lr=6.10e-05 elapsed=1757s
+[qwen] step 2400 val_loss=1.7449
+[qwen] step 2420/3375 loss=1.8862 lr=5.87e-05 elapsed=1774s
+[qwen] step 2440/3375 loss=1.7318 lr=5.64e-05 elapsed=1787s
+[qwen] step 2450 val_loss=1.7423
+[qwen] step 2460/3375 loss=1.5058 lr=5.42e-05 elapsed=1804s
+[qwen] step 2480/3375 loss=1.5881 lr=5.20e-05 elapsed=1817s
+[qwen] step 2500/3375 loss=2.0155 lr=4.98e-05 elapsed=1830s
+[qwen] step 2500 val_loss=1.7256
+[qwen] step 2520/3375 loss=1.4653 lr=4.77e-05 elapsed=1847s
+[qwen] step 2540/3375 loss=1.8001 lr=4.56e-05 elapsed=1860s
+[qwen] step 2550 val_loss=1.7222
+[qwen] step 2560/3375 loss=1.6649 lr=4.36e-05 elapsed=1877s
+[qwen] step 2580/3375 loss=1.8076 lr=4.15e-05 elapsed=1890s
+[qwen] step 2600/3375 loss=1.7167 lr=3.96e-05 elapsed=1904s
+[qwen] step 2600 val_loss=1.7121
+[qwen] step 2620/3375 loss=1.7201 lr=3.77e-05 elapsed=1921s
+[qwen] step 2640/3375 loss=1.6871 lr=3.58e-05 elapsed=1934s
+[qwen] step 2650 val_loss=1.7063
+[qwen] step 2660/3375 loss=1.7273 lr=3.39e-05 elapsed=1951s
+[qwen] step 2680/3375 loss=1.8623 lr=3.21e-05 elapsed=1964s
+[qwen] step 2700/3375 loss=1.8467 lr=3.04e-05 elapsed=1977s
+[qwen] step 2700 val_loss=1.7038
+[qwen] step 2720/3375 loss=2.0026 lr=3.00e-05 elapsed=1994s
+[qwen] step 2740/3375 loss=1.7542 lr=3.00e-05 elapsed=2007s
+[qwen] step 2750 val_loss=1.6955
+[qwen] step 2760/3375 loss=1.9149 lr=3.00e-05 elapsed=2024s
+[qwen] step 2780/3375 loss=1.5122 lr=3.00e-05 elapsed=2037s
+[qwen] step 2800/3375 loss=1.8656 lr=3.00e-05 elapsed=2050s
+[qwen] step 2800 val_loss=1.6811
+[qwen] step 2820/3375 loss=1.6194 lr=3.00e-05 elapsed=2067s
+[qwen] step 2840/3375 loss=1.8089 lr=3.00e-05 elapsed=2080s
+[qwen] step 2850 val_loss=1.6812
+[qwen] step 2860/3375 loss=1.6801 lr=3.00e-05 elapsed=2097s
+[qwen] step 2880/3375 loss=1.7955 lr=3.00e-05 elapsed=2110s
+[qwen] step 2900/3375 loss=1.5235 lr=3.00e-05 elapsed=2123s
+[qwen] step 2900 val_loss=1.6759
+[qwen] step 2920/3375 loss=1.5176 lr=3.00e-05 elapsed=2140s
+[qwen] step 2940/3375 loss=1.9700 lr=3.00e-05 elapsed=2153s
+[qwen] step 2950 val_loss=1.6699
+[qwen] step 2960/3375 loss=1.6931 lr=3.00e-05 elapsed=2170s
+[qwen] step 2980/3375 loss=1.2598 lr=3.00e-05 elapsed=2184s
+[qwen] step 3000/3375 loss=1.7759 lr=3.00e-05 elapsed=2197s
+[qwen] step 3000 val_loss=1.6695
+[qwen] step 3020/3375 loss=1.8400 lr=3.00e-05 elapsed=2214s
+[qwen] step 3040/3375 loss=2.0108 lr=3.00e-05 elapsed=2227s
+[qwen] step 3050 val_loss=1.6695
+[qwen] step 3060/3375 loss=1.6960 lr=3.00e-05 elapsed=2244s
+[qwen] step 3080/3375 loss=1.8539 lr=3.00e-05 elapsed=2257s
+[qwen] step 3100/3375 loss=2.0510 lr=3.00e-05 elapsed=2270s
+[qwen] step 3100 val_loss=1.6593
+[qwen] step 3120/3375 loss=1.8095 lr=3.00e-05 elapsed=2287s
+[qwen] step 3140/3375 loss=1.9223 lr=3.00e-05 elapsed=2300s
+[qwen] step 3150 val_loss=1.6574
+[qwen] step 3160/3375 loss=1.8288 lr=3.00e-05 elapsed=2317s
+[qwen] step 3180/3375 loss=1.8362 lr=3.00e-05 elapsed=2330s
+[qwen] step 3200/3375 loss=1.5401 lr=3.00e-05 elapsed=2343s
+[qwen] step 3200 val_loss=1.6492
+[qwen] step 3220/3375 loss=1.7451 lr=3.00e-05 elapsed=2360s
+[qwen] step 3240/3375 loss=1.8434 lr=3.00e-05 elapsed=2373s
+[qwen] step 3250 val_loss=1.7040
+[qwen] step 3260/3375 loss=1.9270 lr=3.00e-05 elapsed=2390s
+[qwen] step 3280/3375 loss=1.5928 lr=3.00e-05 elapsed=2403s
+[qwen] step 3300/3375 loss=1.5423 lr=3.00e-05 elapsed=2416s
+[qwen] step 3300 val_loss=1.6538
+[qwen] step 3320/3375 loss=1.8096 lr=3.00e-05 elapsed=2433s
+[qwen] step 3340/3375 loss=1.5222 lr=3.00e-05 elapsed=2446s
+[qwen] step 3350 val_loss=1.6443
+[qwen] step 3360/3375 loss=1.5593 lr=3.00e-05 elapsed=2463s
+[qwen] FINAL val_loss=1.6438
+Done. Best val_loss=1.0480 at step 100  path=/data/user_data/jgai/hybrid-code-gen/ckpt/full/02_lr3e-4/02_single_ar/step100-val1.0480

02_lr3e-4/02_single_ar/config.json

@@ -0,0 +1,31 @@
+{
+  "base_model": "Qwen/Qwen2.5-Coder-1.5B",
+  "train_jsonl": "/data/user_data/jgai/hybrid-code-gen/data/stack10k/train.jsonl",
+  "val_jsonl": "/data/user_data/jgai/hybrid-code-gen/data/stack10k/val.jsonl",
+  "output_dir": "/data/user_data/jgai/hybrid-code-gen/ckpt/full/02_lr3e-4/02_single_ar",
+  "lora_r": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "lora_target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "max_steps": 3375,
+  "batch_size": 1,
+  "grad_accum": 1,
+  "lr": 0.0003,
+  "weight_decay": 0.01,
+  "warmup_steps": 100,
+  "grad_clip": 1.0,
+  "max_seq_len": 2048,
+  "loss_scope": "full",
+  "log_interval": 20,
+  "eval_interval": 50,
+  "save_interval": 1000,
+  "seed": 42
+}

02_lr3e-4/02_single_ar/step100-val1.0480/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

02_lr3e-4/02_single_ar/step100-val1.0480/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

02_lr3e-4/02_single_ar/step100-val1.0480/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ec6fe0e8b55213e7a39dbc379ec1525e8fe7db3a9f86118a8e65878904d6e7
+size 1079797096

02_lr3e-4/02_single_ar/step100-val1.0480/added_tokens.json

@@ -0,0 +1,56 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|body_0|>": 151667,
+  "<|body_1|>": 151668,
+  "<|body_2|>": 151669,
+  "<|body_3|>": 151670,
+  "<|body_4|>": 151671,
+  "<|body_5|>": 151672,
+  "<|body_6|>": 151673,
+  "<|body_7|>": 151674,
+  "<|body_8|>": 151675,
+  "<|body_9|>": 151676,
+  "<|body_start_0|>": 151677,
+  "<|body_start_1|>": 151678,
+  "<|body_start_2|>": 151679,
+  "<|body_start_3|>": 151680,
+  "<|body_start_4|>": 151681,
+  "<|body_start_5|>": 151682,
+  "<|body_start_6|>": 151683,
+  "<|body_start_7|>": 151684,
+  "<|body_start_8|>": 151685,
+  "<|body_start_9|>": 151686,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|end_body_0|>": 151687,
+  "<|end_body_1|>": 151688,
+  "<|end_body_2|>": 151689,
+  "<|end_body_3|>": 151690,
+  "<|end_body_4|>": 151691,
+  "<|end_body_5|>": 151692,
+  "<|end_body_6|>": 151693,
+  "<|end_body_7|>": 151694,
+  "<|end_body_8|>": 151695,
+  "<|end_body_9|>": 151696,
+  "<|end_skeleton|>": 151666,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|skeleton|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

02_lr3e-4/02_single_ar/step100-val1.0480/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

02_lr3e-4/02_single_ar/step100-val1.0480/special_tokens_map.json

@@ -0,0 +1,242 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

02_lr3e-4/02_single_ar/step100-val1.0480/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e418905c4788c5f5ea0dd1ca15c904591f50fce71e16fc311f1b4d84e7ed50d8
+size 11428087

02_lr3e-4/02_single_ar/step100-val1.0480/tokenizer_config.json

@@ -0,0 +1,482 @@
+{
+  "add_bos_token": false,
+  "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": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|end_skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151676": {
+      "content": "<|body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<|body_start_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<|body_start_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<|body_start_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<|body_start_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<|body_start_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<|body_start_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<|body_start_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<|body_start_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<|body_start_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<|body_start_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<|end_body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<|end_body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<|end_body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<|end_body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<|end_body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<|end_body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<|end_body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<|end_body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<|end_body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<|end_body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|skeleton|>",
+    "<|end_skeleton|>",
+    "<|body_0|>",
+    "<|body_1|>",
+    "<|body_2|>",
+    "<|body_3|>",
+    "<|body_4|>",
+    "<|body_5|>",
+    "<|body_6|>",
+    "<|body_7|>",
+    "<|body_8|>",
+    "<|body_9|>",
+    "<|body_start_0|>",
+    "<|body_start_1|>",
+    "<|body_start_2|>",
+    "<|body_start_3|>",
+    "<|body_start_4|>",
+    "<|body_start_5|>",
+    "<|body_start_6|>",
+    "<|body_start_7|>",
+    "<|body_start_8|>",
+    "<|body_start_9|>",
+    "<|end_body_0|>",
+    "<|end_body_1|>",
+    "<|end_body_2|>",
+    "<|end_body_3|>",
+    "<|end_body_4|>",
+    "<|end_body_5|>",
+    "<|end_body_6|>",
+    "<|end_body_7|>",
+    "<|end_body_8|>",
+    "<|end_body_9|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

02_lr3e-4/02_single_ar/step50-val0.9958/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

02_lr3e-4/02_single_ar/step50-val0.9958/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

02_lr3e-4/02_single_ar/step50-val0.9958/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a86f1e6a93be2a795114c4afb12bbb0cf6f00d21b4e9c88a050a4458ab4e2a
+size 1079797096

02_lr3e-4/02_single_ar/step50-val0.9958/added_tokens.json

@@ -0,0 +1,56 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|body_0|>": 151667,
+  "<|body_1|>": 151668,
+  "<|body_2|>": 151669,
+  "<|body_3|>": 151670,
+  "<|body_4|>": 151671,
+  "<|body_5|>": 151672,
+  "<|body_6|>": 151673,
+  "<|body_7|>": 151674,
+  "<|body_8|>": 151675,
+  "<|body_9|>": 151676,
+  "<|body_start_0|>": 151677,
+  "<|body_start_1|>": 151678,
+  "<|body_start_2|>": 151679,
+  "<|body_start_3|>": 151680,
+  "<|body_start_4|>": 151681,
+  "<|body_start_5|>": 151682,
+  "<|body_start_6|>": 151683,
+  "<|body_start_7|>": 151684,
+  "<|body_start_8|>": 151685,
+  "<|body_start_9|>": 151686,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|end_body_0|>": 151687,
+  "<|end_body_1|>": 151688,
+  "<|end_body_2|>": 151689,
+  "<|end_body_3|>": 151690,
+  "<|end_body_4|>": 151691,
+  "<|end_body_5|>": 151692,
+  "<|end_body_6|>": 151693,
+  "<|end_body_7|>": 151694,
+  "<|end_body_8|>": 151695,
+  "<|end_body_9|>": 151696,
+  "<|end_skeleton|>": 151666,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|skeleton|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

02_lr3e-4/02_single_ar/step50-val0.9958/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

02_lr3e-4/02_single_ar/step50-val0.9958/special_tokens_map.json

@@ -0,0 +1,242 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|body_start_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

02_lr3e-4/02_single_ar/step50-val0.9958/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e418905c4788c5f5ea0dd1ca15c904591f50fce71e16fc311f1b4d84e7ed50d8
+size 11428087

02_lr3e-4/02_single_ar/step50-val0.9958/tokenizer_config.json

@@ -0,0 +1,482 @@
+{
+  "add_bos_token": false,
+  "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": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|end_skeleton|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151676": {
+      "content": "<|body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<|body_start_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<|body_start_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<|body_start_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<|body_start_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<|body_start_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<|body_start_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<|body_start_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<|body_start_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<|body_start_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<|body_start_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<|end_body_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<|end_body_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<|end_body_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<|end_body_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<|end_body_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<|end_body_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<|end_body_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<|end_body_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<|end_body_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<|end_body_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|skeleton|>",
+    "<|end_skeleton|>",
+    "<|body_0|>",
+    "<|body_1|>",
+    "<|body_2|>",
+    "<|body_3|>",
+    "<|body_4|>",
+    "<|body_5|>",
+    "<|body_6|>",
+    "<|body_7|>",
+    "<|body_8|>",
+    "<|body_9|>",
+    "<|body_start_0|>",
+    "<|body_start_1|>",
+    "<|body_start_2|>",
+    "<|body_start_3|>",
+    "<|body_start_4|>",
+    "<|body_start_5|>",
+    "<|body_start_6|>",
+    "<|body_start_7|>",
+    "<|body_start_8|>",
+    "<|body_start_9|>",
+    "<|end_body_0|>",
+    "<|end_body_1|>",
+    "<|end_body_2|>",
+    "<|end_body_3|>",
+    "<|end_body_4|>",
+    "<|end_body_5|>",
+    "<|end_body_6|>",
+    "<|end_body_7|>",
+    "<|end_body_8|>",
+    "<|end_body_9|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

02_lr3e-4/02_single_ar/topk_val.json

@@ -0,0 +1,14 @@
+[
+  {
+    "rank": 0,
+    "val_loss": 1.0479745119810104,
+    "step": 100,
+    "path": "/data/user_data/jgai/hybrid-code-gen/ckpt/full/02_lr3e-4/02_single_ar/step100-val1.0480"
+  },
+  {
+    "rank": 1,
+    "val_loss": 0.9957711786031723,
+    "step": 50,
+    "path": "/data/user_data/jgai/hybrid-code-gen/ckpt/full/02_lr3e-4/02_single_ar/step50-val0.9958"
+  }
+]