diff --git "a/novel-translation/09_tune-lf-medium-py3.11.ipynb" "b/novel-translation/09_tune-lf-medium-py3.11.ipynb"
--- "a/novel-translation/09_tune-lf-medium-py3.11.ipynb"
+++ "b/novel-translation/09_tune-lf-medium-py3.11.ipynb"
@@ -304,7 +304,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Fri Jul  5 08:59:30 2024       \r\n+---------------------------------------------------------------------------------------+\r\n| NVIDIA-SMI 535.54.03              Driver Version: 535.54.03    CUDA Version: 12.2     |\r\n|-----------------------------------------+----------------------+----------------------+\r\n| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |\r\n| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |\r\n|                                         |                      |               MIG M. |\r\n|=========================================+======================+======================|\r\n|   0  Tesla T4                       Off | 00000001:00:00.0 Off |                    0 |\r\n| N/A   31C    P8               9W /  70W |      2MiB / 15360MiB |      0%      Default |\r\n|                                         |                      |                  N/A |\r\n+-----------------------------------------+----------------------+----------------------+\r\n                                                                                         \r\n+---------------------------------------------------------------------------------------+\r\n| Processes:                                                                            |\r\n|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |\r\n|        ID   ID                                                             Usage      |\r\n|=======================================================================================|\r\n|  No running processes found                                                           |\r\n+---------------------------------------------------------------------------------------+\r\n"
+      "Sat Jul  6 05:25:48 2024       \r\n+---------------------------------------------------------------------------------------+\r\n| NVIDIA-SMI 535.54.03              Driver Version: 535.54.03    CUDA Version: 12.2     |\r\n|-----------------------------------------+----------------------+----------------------+\r\n| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |\r\n| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |\r\n|                                         |                      |               MIG M. |\r\n|=========================================+======================+======================|\r\n|   0  Tesla T4                       Off | 00000001:00:00.0 Off |                    0 |\r\n| N/A   63C    P8              11W /  70W |      2MiB / 15360MiB |      0%      Default |\r\n|                                         |                      |                  N/A |\r\n+-----------------------------------------+----------------------+----------------------+\r\n                                                                                         \r\n+---------------------------------------------------------------------------------------+\r\n| Processes:                                                                            |\r\n|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |\r\n|        ID   ID                                                             Usage      |\r\n|=======================================================================================|\r\n|  No running processes found                                                           |\r\n+---------------------------------------------------------------------------------------+\r\n"
      ]
     }
    ],
@@ -333,7 +333,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Python 3.11.0rc1\r\nName: flash-attn\nVersion: 2.5.9.post1\nSummary: Flash Attention: Fast and Memory-Efficient Exact Attention\nHome-page: https://github.com/Dao-AILab/flash-attention\nAuthor: Tri Dao\nAuthor-email: trid@cs.stanford.edu\nLicense: \nLocation: /local_disk0/.ephemeral_nfs/envs/pythonEnv-40f92d71-6c52-44a3-a1ef-62cdea633f68/lib/python3.11/site-packages\nRequires: einops, torch\nRequired-by: \nCPU times: user 10.5 ms, sys: 15.1 ms, total: 25.6 ms\nWall time: 4.37 s\n"
+      "Python 3.11.0rc1\r\nName: flash-attn\nVersion: 2.5.9.post1\nSummary: Flash Attention: Fast and Memory-Efficient Exact Attention\nHome-page: https://github.com/Dao-AILab/flash-attention\nAuthor: Tri Dao\nAuthor-email: trid@cs.stanford.edu\nLicense: \nLocation: /local_disk0/.ephemeral_nfs/envs/pythonEnv-40f92d71-6c52-44a3-a1ef-62cdea633f68/lib/python3.11/site-packages\nRequires: einops, torch\nRequired-by: \nCPU times: user 10.1 ms, sys: 14.5 ms, total: 24.6 ms\nWall time: 4.25 s\n"
      ]
     }
    ],
@@ -364,7 +364,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Current Directory:\r\n/Workspace/Users/donghao.huang@mastercard.com/llm-finetuning/llama-factory\r\nconfig/llama3_8b_lora_sft.yaml:\r\n {\r\n  \"model_name_or_path\": \"gradientai/Llama-3-8B-Instruct-Gradient-1048k\",\r\n  \"stage\": \"sft\",\r\n  \"do_train\": true,\r\n  \"finetuning_type\": \"lora\",\r\n  \"lora_target\": \"all\",\r\n  \"quantization_bit\": 4,\r\n  \"loraplus_lr_ratio\": 16.0,\r\n  \"dataset\": \"alpaca_mac\",\r\n  \"template\": \"llama3\",\r\n  \"cutoff_len\": 1024,\r\n  \"max_samples\": 4528,\r\n  \"overwrite_cache\": true,\r\n  \"preprocessing_num_workers\": 16,\r\n  \"output_dir\": \"/Workspace/Users/donghao.huang@mastercard.com/lf-saves/llama3-8b/lora/sft/\",\r\n  \"logging_steps\": 10,\r\n  \"save_steps\": 560,\r\n  \"plot_loss\": true,\r\n  \"overwrite_output_dir\": true,\r\n  \"per_device_train_batch_size\": 1,\r\n  \"gradient_accumulation_steps\": 8,\r\n  \"learning_rate\": 0.0001,\r\n  \"num_train_epochs\": 6.0,\r\n  \"lr_scheduler_type\": \"cosine\",\r\n  \"warmup_ratio\": 0.1,\r\n  \"bf16\": true,\r\n  \"ddp_timeout\": 180000000,\r\n  \"val_size\": 0.01,\r\n  \"per_device_eval_batch_size\": 1,\r\n  \"eval_strategy\": \"steps\",\r\n  \"eval_steps\": 560,\r\n  \"report_to\": \"none\"\r\n}\r\n2024-07-05 08:59:40.790008: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\r\nTo enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\r\n[2024-07-05 08:59:50,632] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n07/05/2024 08:59:58 - WARNING - llamafactory.hparams.parser - We recommend enable `upcast_layernorm` in quantized training.\r\n07/05/2024 08:59:58 - INFO - llamafactory.hparams.parser - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-05 08:59:59,223 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/tokenizer.json\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-05 08:59:59,223 >> loading file added_tokens.json from cache at None\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-05 08:59:59,223 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/special_tokens_map.json\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-05 08:59:59,223 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/tokenizer_config.json\r\n[WARNING|logging.py:313] 2024-07-05 08:59:59,517 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\r\n07/05/2024 08:59:59 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>\r\n07/05/2024 08:59:59 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>\r\n07/05/2024 08:59:59 - INFO - llamafactory.data.loader - Loading dataset alpaca_mac.json...\r\n\rConverting format of dataset (num_proc=16):   0%| | 0/4528 [00:00<?, ? examples/\rConverting format of dataset (num_proc=16): 100%|█| 4528/4528 [00:00<00:00, 4511\rConverting format of dataset (num_proc=16): 100%|█| 4528/4528 [00:00<00:00, 2532\r\n\rRunning tokenizer on dataset (num_proc=16):   0%| | 0/4528 [00:00<?, ? examples/\rRunning tokenizer on dataset (num_proc=16):   6%| | 283/4528 [00:00<00:08, 500.4\rRunning tokenizer on dataset (num_proc=16):  12%|▏| 566/4528 [00:00<00:04, 830.0\rRunning tokenizer on dataset (num_proc=16):  19%|▏| 849/4528 [00:00<00:03, 1104.\rRunning tokenizer on dataset (num_proc=16):  25%|▎| 1132/4528 [00:01<00:02, 1305\rRunning tokenizer on dataset (num_proc=16):  31%|▎| 1415/4528 [00:01<00:02, 1518\rRunning tokenizer on dataset (num_proc=16):  38%|▍| 1698/4528 [00:01<00:01, 1657\rRunning tokenizer on dataset (num_proc=16):  44%|▍| 1981/4528 [00:01<00:01, 1724\rRunning tokenizer on dataset (num_proc=16):  50%|▌| 2264/4528 [00:01<00:01, 1759\rRunning tokenizer on dataset (num_proc=16):  56%|▌| 2547/4528 [00:01<00:01, 1752\rRunning tokenizer on dataset (num_proc=16):  62%|▋| 2830/4528 [00:01<00:00, 1770\rRunning tokenizer on dataset (num_proc=16):  69%|▋| 3113/4528 [00:02<00:00, 1866\rRunning tokenizer on dataset (num_proc=16):  75%|▊| 3396/4528 [00:02<00:00, 1937\rRunning tokenizer on dataset (num_proc=16):  81%|▊| 3679/4528 [00:02<00:00, 1988\rRunning tokenizer on dataset (num_proc=16):  88%|▉| 3962/4528 [00:02<00:00, 2034\rRunning tokenizer on dataset (num_proc=16):  94%|▉| 4245/4528 [00:02<00:00, 2042\rRunning tokenizer on dataset (num_proc=16): 100%|█| 4528/4528 [00:02<00:00, 2095\rRunning tokenizer on dataset (num_proc=16): 100%|█| 4528/4528 [00:02<00:00, 1599\r\ninput_ids:\r\n[128000, 128006, 882, 128007, 271, 5618, 15025, 279, 2768, 8620, 1495, 1139, 6498, 323, 3493, 1193, 279, 25548, 2262, 11, 4400, 775, 627, 37087, 6271, 245, 100815, 121991, 110139, 113265, 108057, 1811, 128009, 128006, 78191, 128007, 271, 18433, 358, 574, 2682, 555, 264, 39935, 45586, 13, 128009]\r\ninputs:\r\n<|begin_of_text|><|start_header_id|>user<|end_header_id|>\r\n\r\nPlease translate the following Chinese text into English and provide only the translated content, nothing else.\r\n全仗着狐仙搭救。<|eot_id|><|start_header_id|>assistant<|end_header_id|>\r\n\r\nBecause I was protected by a fox fairy.<|eot_id|>\r\nlabel_ids:\r\n[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 18433, 358, 574, 2682, 555, 264, 39935, 45586, 13, 128009]\r\nlabels:\r\nBecause I was protected by a fox fairy.<|eot_id|>\r\n[INFO|configuration_utils.py:733] 2024-07-05 09:00:03,851 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/config.json\r\n[INFO|configuration_utils.py:800] 2024-07-05 09:00:03,852 >> Model config LlamaConfig {\r\n  \"_name_or_path\": \"gradientai/Llama-3-8B-Instruct-Gradient-1048k\",\r\n  \"architectures\": [\r\n    \"LlamaForCausalLM\"\r\n  ],\r\n  \"attention_bias\": false,\r\n  \"attention_dropout\": 0.0,\r\n  \"bos_token_id\": 128000,\r\n  \"eos_token_id\": 128001,\r\n  \"hidden_act\": \"silu\",\r\n  \"hidden_size\": 4096,\r\n  \"initializer_range\": 0.02,\r\n  \"intermediate_size\": 14336,\r\n  \"max_position_embeddings\": 1048576,\r\n  \"mlp_bias\": false,\r\n  \"model_type\": \"llama\",\r\n  \"num_attention_heads\": 32,\r\n  \"num_hidden_layers\": 32,\r\n  \"num_key_value_heads\": 8,\r\n  \"pretraining_tp\": 1,\r\n  \"rms_norm_eps\": 1e-05,\r\n  \"rope_scaling\": null,\r\n  \"rope_theta\": 3580165449.0,\r\n  \"tie_word_embeddings\": false,\r\n  \"torch_dtype\": \"bfloat16\",\r\n  \"transformers_version\": \"4.42.3\",\r\n  \"use_cache\": true,\r\n  \"vocab_size\": 128256\r\n}\r\n\r\n07/05/2024 09:00:03 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\r\n[INFO|modeling_utils.py:3556] 2024-07-05 09:00:03,878 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/model.safetensors.index.json\r\n[INFO|modeling_utils.py:1531] 2024-07-05 09:00:03,880 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.\r\n[INFO|configuration_utils.py:1000] 2024-07-05 09:00:03,881 >> Generate config GenerationConfig {\r\n  \"bos_token_id\": 128000,\r\n  \"eos_token_id\": 128001\r\n}\r\n\r\n\rLoading checkpoint shards:   0%|                          | 0/4 [00:00<?, ?it/s]\rLoading checkpoint shards:  25%|████▌             | 1/4 [00:01<00:03,  1.19s/it]\rLoading checkpoint shards:  50%|█████████         | 2/4 [00:02<00:02,  1.15s/it]\rLoading checkpoint shards:  75%|█████████████▌    | 3/4 [00:03<00:01,  1.12s/it]\rLoading checkpoint shards: 100%|██████████████████| 4/4 [00:03<00:00,  1.16it/s]\rLoading checkpoint shards: 100%|██████████████████| 4/4 [00:03<00:00,  1.04it/s]\r\n[INFO|modeling_utils.py:4364] 2024-07-05 09:00:08,031 >> All model checkpoint weights were used when initializing LlamaForCausalLM.\r\n\r\n[INFO|modeling_utils.py:4372] 2024-07-05 09:00:08,031 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at gradientai/Llama-3-8B-Instruct-Gradient-1048k.\r\nIf your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.\r\n[INFO|configuration_utils.py:955] 2024-07-05 09:00:08,056 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/generation_config.json\r\n[INFO|configuration_utils.py:1000] 2024-07-05 09:00:08,057 >> Generate config GenerationConfig {\r\n  \"bos_token_id\": 128000,\r\n  \"do_sample\": true,\r\n  \"eos_token_id\": [\r\n    128001,\r\n    128009\r\n  ],\r\n  \"max_length\": 4096,\r\n  \"temperature\": 0.6,\r\n  \"top_p\": 0.9\r\n}\r\n\r\n07/05/2024 09:00:08 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.\r\n07/05/2024 09:00:08 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\r\n07/05/2024 09:00:08 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.\r\n07/05/2024 09:00:08 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA\r\n07/05/2024 09:00:08 - INFO - llamafactory.model.model_utils.misc - Found linear modules: gate_proj,v_proj,o_proj,k_proj,up_proj,down_proj,q_proj\r\n07/05/2024 09:00:08 - INFO - llamafactory.model.loader - trainable params: 20,971,520 || all params: 8,051,232,768 || trainable%: 0.2605\r\n[INFO|trainer.py:642] 2024-07-05 09:00:09,078 >> Using auto half precision backend\r\ntraining_args.resume_from_checkpoint: None\r\n07/05/2024 09:00:09 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.\r\n[INFO|trainer.py:2128] 2024-07-05 09:00:09,496 >> ***** Running training *****\r\n[INFO|trainer.py:2129] 2024-07-05 09:00:09,496 >>   Num examples = 4,482\r\n[INFO|trainer.py:2130] 2024-07-05 09:00:09,496 >>   Num Epochs = 6\r\n[INFO|trainer.py:2131] 2024-07-05 09:00:09,496 >>   Instantaneous batch size per device = 1\r\n[INFO|trainer.py:2134] 2024-07-05 09:00:09,496 >>   Total train batch size (w. parallel, distributed & accumulation) = 8\r\n[INFO|trainer.py:2135] 2024-07-05 09:00:09,496 >>   Gradient Accumulation steps = 8\r\n[INFO|trainer.py:2136] 2024-07-05 09:00:09,496 >>   Total optimization steps = 3,360\r\n[INFO|trainer.py:2137] 2024-07-05 09:00:09,500 >>   Number of trainable parameters = 20,971,520\r\n\r  0%|                                                  | 0/3360 [00:00<?, ?it/s]\r  0%|                                       | 1/3360 [00:24<23:13:32, 24.89s/it]\r  0%|                                       | 2/3360 [00:50<23:50:05, 25.55s/it]\r  0%|                                       | 3/3360 [01:14<22:51:20, 24.51s/it]\r  0%|                                       | 4/3360 [01:33<21:02:08, 22.57s/it]\r  0%|                                       | 5/3360 [02:02<23:03:53, 24.75s/it]\r  0%|                                       | 6/3360 [02:29<23:55:47, 25.69s/it]\r  0%|                                       | 7/3360 [02:53<23:16:25, 24.99s/it]\r  0%|                                       | 8/3360 [03:17<23:05:59, 24.81s/it]\r  0%|                                       | 9/3360 [03:44<23:44:38, 25.51s/it]\r  0%|                                      | 10/3360 [04:12<24:15:39, 26.07s/it]\r                                                                                \r{'loss': 2.2828, 'grad_norm': 1.950901985168457, 'learning_rate': 2.9761904761904763e-06, 'epoch': 0.02}\r\n\r  0%|                                      | 10/3360 [04:12<24:15:39, 26.07s/it]\r  0%|                                      | 11/3360 [04:38<24:19:21, 26.15s/it]\r  0%|▏                                     | 12/3360 [05:05<24:25:37, 26.27s/it]\r  0%|▏                                     | 13/3360 [05:28<23:38:04, 25.42s/it]\r  0%|▏                                     | 14/3360 [05:54<23:39:03, 25.45s/it]\r  0%|▏                                     | 15/3360 [06:18<23:29:46, 25.29s/it]\r  0%|▏                                     | 16/3360 [06:49<24:51:42, 26.77s/it]\r  1%|▏                                     | 17/3360 [07:12<23:53:43, 25.73s/it]\r  1%|▏                                     | 18/3360 [07:36<23:30:52, 25.33s/it]\r  1%|▏                                     | 19/3360 [08:04<24:09:51, 26.04s/it]\r  1%|▏                                     | 20/3360 [08:28<23:27:42, 25.29s/it]\r                                                                                \r{'loss': 2.1958, 'grad_norm': 2.308849334716797, 'learning_rate': 5.9523809523809525e-06, 'epoch': 0.04}\r\n\r  1%|▏                                     | 20/3360 [08:28<23:27:42, 25.29s/it]\r  1%|▏                                     | 21/3360 [08:54<23:50:16, 25.70s/it]\r  1%|▏                                     | 22/3360 [09:17<22:53:13, 24.68s/it]\r  1%|▎                                     | 23/3360 [09:40<22:27:22, 24.23s/it]\r  1%|▎                                     | 24/3360 [10:05<22:39:04, 24.44s/it]\r  1%|▎                                     | 25/3360 [10:25<21:32:21, 23.25s/it]\r  1%|▎                                     | 26/3360 [10:48<21:22:09, 23.07s/it]\r  1%|▎                                     | 27/3360 [11:15<22:36:12, 24.41s/it]\r  1%|▎                                     | 28/3360 [11:45<23:59:09, 25.92s/it]\r  1%|▎                                     | 29/3360 [12:08<23:11:50, 25.07s/it]\r  1%|▎                                     | 30/3360 [12:34<23:36:16, 25.52s/it]\r                                                                                \r{'loss': 1.8784, 'grad_norm': 1.3710776567459106, 'learning_rate': 8.92857142857143e-06, 'epoch': 0.05}\r\n\r  1%|▎                                     | 30/3360 [12:34<23:36:16, 25.52s/it]\r  1%|▎                                     | 31/3360 [12:56<22:33:30, 24.39s/it]\r  1%|▎                                     | 32/3360 [13:18<21:50:39, 23.63s/it]\r  1%|▎                                     | 33/3360 [13:39<21:01:51, 22.76s/it]\r  1%|▍                                     | 34/3360 [14:03<21:27:00, 23.22s/it]\r  1%|▍                                     | 35/3360 [14:29<22:09:41, 23.99s/it]\r  1%|▍                                     | 36/3360 [14:52<21:56:18, 23.76s/it]\r  1%|▍                                     | 37/3360 [15:17<22:19:30, 24.19s/it]\r  1%|▍                                     | 38/3360 [15:40<21:55:15, 23.76s/it]\r  1%|▍                                     | 39/3360 [16:05<22:19:32, 24.20s/it]\r  1%|▍                                     | 40/3360 [16:27<21:35:11, 23.41s/it]\r                                                                                \r{'loss': 1.7298, 'grad_norm': 3.4520955085754395, 'learning_rate': 1.1904761904761905e-05, 'epoch': 0.07}\r\n\r  1%|▍                                     | 40/3360 [16:27<21:35:11, 23.41s/it]\r  1%|▍                                     | 41/3360 [16:53<22:20:23, 24.23s/it]\r  1%|▍                                     | 42/3360 [17:20<23:06:10, 25.07s/it]\r  1%|▍                                     | 43/3360 [17:46<23:21:49, 25.36s/it]\r  1%|▍                                     | 44/3360 [18:09<22:48:06, 24.75s/it]\r  1%|▌                                     | 45/3360 [18:34<22:39:34, 24.61s/it]\r  1%|▌                                     | 46/3360 [19:00<23:02:50, 25.04s/it]\r  1%|▌                                     | 47/3360 [19:28<24:02:09, 26.12s/it]\r  1%|▌                                     | 48/3360 [19:53<23:40:33, 25.73s/it]\r  1%|▌                                     | 49/3360 [20:20<23:53:15, 25.97s/it]\r  1%|▌                                     | 50/3360 [20:47<24:09:18, 26.27s/it]\r                                                                                \r{'loss': 1.8498, 'grad_norm': 1.293561577796936, 'learning_rate': 1.4880952380952381e-05, 'epoch': 0.09}\r\n\r  1%|▌                                     | 50/3360 [20:47<24:09:18, 26.27s/it]\r  2%|▌                                     | 51/3360 [21:14<24:25:27, 26.57s/it]\r  2%|▌                                     | 52/3360 [21:35<22:59:55, 25.03s/it]\r  2%|▌                                     | 53/3360 [22:00<22:48:43, 24.83s/it]\r  2%|▌                                     | 54/3360 [22:26<23:05:56, 25.15s/it]\r  2%|▌                                     | 55/3360 [22:49<22:39:11, 24.68s/it]\r  2%|▋                                     | 56/3360 [23:16<23:08:32, 25.22s/it]\r  2%|▋                                     | 57/3360 [23:40<22:47:55, 24.85s/it]\r  2%|▋                                     | 58/3360 [24:00<21:37:54, 23.58s/it]\r  2%|▋                                     | 59/3360 [24:29<22:59:23, 25.07s/it]\r  2%|▋                                     | 60/3360 [24:54<23:00:56, 25.11s/it]\r                                                                                \r{'loss': 1.6822, 'grad_norm': 2.2295732498168945, 'learning_rate': 1.785714285714286e-05, 'epoch': 0.11}\r\n\r  2%|▋                                     | 60/3360 [24:54<23:00:56, 25.11s/it]\r  2%|▋                                     | 61/3360 [25:21<23:28:25, 25.62s/it]\r  2%|▋                                     | 62/3360 [25:49<24:07:28, 26.33s/it]\r  2%|▋                                     | 63/3360 [26:11<22:58:26, 25.09s/it]\r  2%|▋                                     | 64/3360 [26:37<23:13:44, 25.37s/it]\r  2%|▋                                     | 65/3360 [27:01<22:44:02, 24.84s/it]\r  2%|▋                                     | 66/3360 [27:26<22:48:54, 24.93s/it]\r  2%|▊                                     | 67/3360 [27:49<22:14:18, 24.31s/it]\r  2%|▊                                     | 68/3360 [28:12<22:01:07, 24.08s/it]\r  2%|▊                                     | 69/3360 [28:39<22:38:11, 24.76s/it]\r  2%|▊                                     | 70/3360 [29:03<22:37:06, 24.75s/it]\r                                                                                \r{'loss': 1.7621, 'grad_norm': 1.627418041229248, 'learning_rate': 2.0833333333333336e-05, 'epoch': 0.12}\r\n\r  2%|▊                                     | 70/3360 [29:03<22:37:06, 24.75s/it]\r  2%|▊                                     | 71/3360 [29:27<22:18:57, 24.43s/it]\r  2%|▊                                     | 72/3360 [29:51<22:11:29, 24.30s/it]\r  2%|▊                                     | 73/3360 [30:19<23:11:26, 25.40s/it]\r  2%|▊                                     | 74/3360 [30:46<23:37:59, 25.89s/it]\r  2%|▊                                     | 75/3360 [31:16<24:43:13, 27.09s/it]\r  2%|▊                                     | 76/3360 [31:39<23:35:14, 25.86s/it]\r  2%|▊                                     | 77/3360 [32:07<24:12:33, 26.55s/it]\r  2%|▉                                     | 78/3360 [32:33<24:05:03, 26.42s/it]\r  2%|▉                                     | 79/3360 [33:04<25:15:23, 27.71s/it]\r  2%|▉                                     | 80/3360 [33:28<24:09:50, 26.52s/it]\r                                                                                \r{'loss': 1.6161, 'grad_norm': 1.4014948606491089, 'learning_rate': 2.380952380952381e-05, 'epoch': 0.14}\r\n\r  2%|▉                                     | 80/3360 [33:28<24:09:50, 26.52s/it]\r  2%|▉                                     | 81/3360 [33:53<23:46:34, 26.10s/it]\r  2%|▉                                     | 82/3360 [34:16<23:01:55, 25.29s/it]\r  2%|▉                                     | 83/3360 [34:40<22:32:02, 24.76s/it]\r  2%|▉                                     | 84/3360 [35:02<21:55:05, 24.09s/it]\r  3%|▉                                     | 85/3360 [35:27<22:14:15, 24.44s/it]\r  3%|▉                                     | 86/3360 [35:54<22:43:08, 24.98s/it]\r  3%|▉                                     | 87/3360 [36:20<23:01:26, 25.32s/it]\r  3%|▉                                     | 88/3360 [36:47<23:35:04, 25.95s/it]\r  3%|█                                     | 89/3360 [37:12<23:22:41, 25.73s/it]\r  3%|█                                     | 90/3360 [37:39<23:42:01, 26.09s/it]\r                                                                                \r{'loss': 1.7168, 'grad_norm': 2.215449094772339, 'learning_rate': 2.6785714285714288e-05, 'epoch': 0.16}\r\n\r  3%|█                                     | 90/3360 [37:39<23:42:01, 26.09s/it]\r  3%|█                                     | 91/3360 [38:06<23:48:38, 26.22s/it]\r  3%|█                                     | 92/3360 [38:32<23:47:35, 26.21s/it]\r  3%|█                                     | 93/3360 [38:59<24:04:10, 26.52s/it]\r  3%|█                                     | 94/3360 [39:30<25:13:10, 27.80s/it]\r  3%|█                                     | 95/3360 [39:54<24:05:29, 26.56s/it]\r  3%|█                                     | 96/3360 [40:16<22:49:41, 25.18s/it]\r  3%|█                                     | 97/3360 [40:40<22:29:01, 24.81s/it]\r  3%|█                                     | 98/3360 [41:04<22:14:36, 24.55s/it]\r  3%|█                                     | 99/3360 [41:27<21:52:18, 24.15s/it]\r  3%|█                                    | 100/3360 [41:53<22:26:37, 24.78s/it]\r                                                                                \r{'loss': 1.6314, 'grad_norm': 1.435763955116272, 'learning_rate': 2.9761904761904762e-05, 'epoch': 0.18}\r\n\r  3%|█                                    | 100/3360 [41:53<22:26:37, 24.78s/it]\r  3%|█                                    | 101/3360 [42:18<22:21:30, 24.70s/it]\r  3%|█                                    | 102/3360 [42:40<21:43:27, 24.00s/it]\r  3%|█▏                                   | 103/3360 [43:03<21:28:23, 23.73s/it]\r  3%|█▏                                   | 104/3360 [43:25<21:06:00, 23.33s/it]\r  3%|█▏                                   | 105/3360 [43:55<22:39:10, 25.05s/it]\r  3%|█▏                                   | 106/3360 [44:22<23:14:24, 25.71s/it]\r  3%|█▏                                   | 107/3360 [44:44<22:17:57, 24.68s/it]\r  3%|█▏                                   | 108/3360 [45:10<22:38:35, 25.07s/it]\r  3%|█▏                                   | 109/3360 [45:36<22:46:53, 25.23s/it]\r  3%|█▏                                   | 110/3360 [46:02<22:57:57, 25.44s/it]\r                                                                                \r{'loss': 1.6137, 'grad_norm': 1.5036354064941406, 'learning_rate': 3.273809523809524e-05, 'epoch': 0.2}\r\n\r  3%|█▏                                   | 110/3360 [46:02<22:57:57, 25.44s/it]\r  3%|█▏                                   | 111/3360 [46:26<22:45:44, 25.22s/it]\r  3%|█▏                                   | 112/3360 [46:52<22:48:02, 25.27s/it]\r  3%|█▏                                   | 113/3360 [47:15<22:12:29, 24.62s/it]\r  3%|█▎                                   | 114/3360 [47:38<21:43:28, 24.09s/it]\r  3%|█▎                                   | 115/3360 [48:01<21:31:59, 23.89s/it]\r  3%|█▎                                   | 116/3360 [48:27<22:09:06, 24.58s/it]\r  3%|█▎                                   | 117/3360 [48:52<22:19:19, 24.78s/it]\r  4%|█▎                                   | 118/3360 [49:21<23:12:39, 25.77s/it]\r  4%|█▎                                   | 119/3360 [49:43<22:14:08, 24.70s/it]\r  4%|█▎                                   | 120/3360 [50:14<24:06:00, 26.78s/it]\r                                                                                \r{'loss': 1.6265, 'grad_norm': 1.6486930847167969, 'learning_rate': 3.571428571428572e-05, 'epoch': 0.21}\r\n\r  4%|█▎                                   | 120/3360 [50:14<24:06:00, 26.78s/it]\r  4%|█▎                                   | 121/3360 [50:39<23:33:40, 26.19s/it]\r  4%|█▎                                   | 122/3360 [51:01<22:28:23, 24.99s/it]\r  4%|█▎                                   | 123/3360 [51:24<21:56:54, 24.41s/it]\r  4%|█▎                                   | 124/3360 [51:48<21:35:11, 24.01s/it]\r  4%|█▍                                   | 125/3360 [52:12<21:39:50, 24.11s/it]\r  4%|█▍                                   | 126/3360 [52:42<23:09:21, 25.78s/it]\r  4%|█▍                                   | 127/3360 [53:08<23:18:50, 25.96s/it]\r  4%|█▍                                   | 128/3360 [53:35<23:39:47, 26.36s/it]\r  4%|█▍                                   | 129/3360 [53:57<22:19:49, 24.88s/it]\r  4%|█▍                                   | 130/3360 [54:24<23:06:58, 25.76s/it]\r                                                                                \r{'loss': 1.6258, 'grad_norm': 2.645925521850586, 'learning_rate': 3.8690476190476195e-05, 'epoch': 0.23}\r\n\r  4%|█▍                                   | 130/3360 [54:24<23:06:58, 25.76s/it]\r  4%|█▍                                   | 131/3360 [54:51<23:22:27, 26.\n\n*** WARNING: max output size exceeded, skipping output. ***\n\n | 281/3360 [1:57:29<21:54:26, 25.61s/it]\r  8%|██▉                                | 282/3360 [1:57:55<22:05:32, 25.84s/it]\r  8%|██▉                                | 283/3360 [1:58:18<21:24:41, 25.05s/it]\r  8%|██▉                                | 284/3360 [1:58:48<22:34:03, 26.41s/it]\r  8%|██▉                                | 285/3360 [1:59:12<21:59:04, 25.74s/it]\r  9%|██▉                                | 286/3360 [1:59:35<21:25:23, 25.09s/it]\r  9%|██▉                                | 287/3360 [2:00:01<21:37:36, 25.34s/it]\r  9%|███                                | 288/3360 [2:00:26<21:30:07, 25.20s/it]\r  9%|███                                | 289/3360 [2:00:50<21:04:34, 24.71s/it]\r  9%|███                                | 290/3360 [2:01:17<21:38:42, 25.38s/it]\r                                                                                \r{'loss': 1.4702, 'grad_norm': 1.9487817287445068, 'learning_rate': 8.630952380952382e-05, 'epoch': 0.52}\r\n\r  9%|███                                | 290/3360 [2:01:17<21:38:42, 25.38s/it]\r  9%|███                                | 291/3360 [2:01:48<23:09:54, 27.17s/it]\r  9%|███                                | 292/3360 [2:02:15<22:58:46, 26.96s/it]\r  9%|███                                | 293/3360 [2:02:41<22:51:44, 26.84s/it]\r  9%|███                                | 294/3360 [2:03:05<22:07:18, 25.97s/it]\r  9%|███                                | 295/3360 [2:03:34<22:57:04, 26.96s/it]\r  9%|███                                | 296/3360 [2:04:01<22:50:25, 26.84s/it]\r  9%|███                                | 297/3360 [2:04:24<21:47:11, 25.61s/it]\r  9%|███                                | 298/3360 [2:04:51<22:19:06, 26.24s/it]\r  9%|███                                | 299/3360 [2:05:19<22:41:32, 26.69s/it]\r  9%|███▏                               | 300/3360 [2:05:42<21:45:49, 25.60s/it]\r                                                                                \r{'loss': 1.5849, 'grad_norm': 3.3946197032928467, 'learning_rate': 8.92857142857143e-05, 'epoch': 0.54}\r\n\r  9%|███▏                               | 300/3360 [2:05:42<21:45:49, 25.60s/it]\r  9%|███▏                               | 301/3360 [2:06:05<21:00:19, 24.72s/it]\r  9%|███▏                               | 302/3360 [2:06:31<21:14:56, 25.02s/it]\r  9%|███▏                               | 303/3360 [2:06:57<21:34:27, 25.41s/it]\r  9%|███▏                               | 304/3360 [2:07:18<20:27:36, 24.10s/it]\r  9%|███▏                               | 305/3360 [2:07:43<20:50:10, 24.55s/it]\r  9%|███▏                               | 306/3360 [2:08:09<21:07:35, 24.90s/it]\r  9%|███▏                               | 307/3360 [2:08:36<21:36:43, 25.48s/it]\r  9%|███▏                               | 308/3360 [2:09:01<21:21:57, 25.20s/it]\r  9%|███▏                               | 309/3360 [2:09:27<21:34:23, 25.46s/it]\r  9%|███▏                               | 310/3360 [2:09:51<21:21:19, 25.21s/it]\r                                                                                \r{'loss': 1.6439, 'grad_norm': 2.366210460662842, 'learning_rate': 9.226190476190478e-05, 'epoch': 0.55}\r\n\r  9%|███▏                               | 310/3360 [2:09:51<21:21:19, 25.21s/it]\r  9%|███▏                               | 311/3360 [2:10:14<20:48:48, 24.57s/it]\r  9%|███▎                               | 312/3360 [2:10:41<21:20:00, 25.20s/it]\r  9%|███▎                               | 313/3360 [2:11:03<20:27:09, 24.16s/it]\r  9%|███▎                               | 314/3360 [2:11:30<21:12:02, 25.06s/it]\r  9%|███▎                               | 315/3360 [2:11:54<21:02:15, 24.87s/it]\r  9%|███▎                               | 316/3360 [2:12:22<21:42:41, 25.68s/it]\r  9%|███▎                               | 317/3360 [2:12:45<21:04:56, 24.94s/it]\r  9%|███▎                               | 318/3360 [2:13:12<21:29:02, 25.43s/it]\r  9%|███▎                               | 319/3360 [2:13:36<21:13:14, 25.12s/it]\r 10%|███▎                               | 320/3360 [2:14:00<21:00:40, 24.88s/it]\r                                                                                \r{'loss': 1.4912, 'grad_norm': 3.868485450744629, 'learning_rate': 9.523809523809524e-05, 'epoch': 0.57}\r\n\r 10%|███▎                               | 320/3360 [2:14:00<21:00:40, 24.88s/it]\r 10%|███▎                               | 321/3360 [2:14:25<20:50:00, 24.68s/it]\r 10%|███▎                               | 322/3360 [2:14:49<20:41:04, 24.51s/it]\r 10%|███▎                               | 323/3360 [2:15:14<20:52:08, 24.74s/it]\r 10%|███▍                               | 324/3360 [2:15:39<20:47:59, 24.66s/it]\r 10%|███▍                               | 325/3360 [2:16:01<20:14:25, 24.01s/it]\r 10%|███▍                               | 326/3360 [2:16:25<20:17:36, 24.08s/it]\r 10%|███▍                               | 327/3360 [2:16:48<19:57:26, 23.69s/it]\r 10%|███▍                               | 328/3360 [2:17:12<20:05:23, 23.85s/it]\r 10%|███▍                               | 329/3360 [2:17:40<20:57:18, 24.89s/it]\r 10%|███▍                               | 330/3360 [2:18:03<20:30:00, 24.36s/it]\r                                                                                \r{'loss': 1.5267, 'grad_norm': 4.594560146331787, 'learning_rate': 9.821428571428572e-05, 'epoch': 0.59}\r\n\r 10%|███▍                               | 330/3360 [2:18:03<20:30:00, 24.36s/it]\r 10%|███▍                               | 331/3360 [2:18:25<20:06:28, 23.90s/it]\r 10%|███▍                               | 332/3360 [2:18:54<21:19:33, 25.35s/it]\r 10%|███▍                               | 333/3360 [2:19:22<21:56:32, 26.10s/it]\r 10%|███▍                               | 334/3360 [2:19:45<21:09:35, 25.17s/it]\r 10%|███▍                               | 335/3360 [2:20:12<21:29:11, 25.57s/it]\r 10%|███▌                               | 336/3360 [2:20:32<20:15:36, 24.12s/it]\r 10%|███▌                               | 337/3360 [2:21:00<21:02:47, 25.06s/it]\r 10%|███▌                               | 338/3360 [2:21:27<21:34:57, 25.71s/it]\r 10%|███▌                               | 339/3360 [2:21:52<21:30:53, 25.64s/it]\r 10%|███▌                               | 340/3360 [2:22:20<22:01:45, 26.26s/it]\r                                                                                \r{'loss': 1.5424, 'grad_norm': 3.0406832695007324, 'learning_rate': 9.999956828659095e-05, 'epoch': 0.61}\r\n\r 10%|███▌                               | 340/3360 [2:22:20<22:01:45, 26.26s/it]\r 10%|███▌                               | 341/3360 [2:22:44<21:28:17, 25.60s/it]\r 10%|███▌                               | 342/3360 [2:23:10<21:38:18, 25.81s/it]\r 10%|███▌                               | 343/3360 [2:23:36<21:39:25, 25.84s/it]\r 10%|███▌                               | 344/3360 [2:24:02<21:39:48, 25.86s/it]\r 10%|███▌                               | 345/3360 [2:24:27<21:30:44, 25.69s/it]\r 10%|███▌                               | 346/3360 [2:24:55<22:05:43, 26.39s/it]\r 10%|███▌                               | 347/3360 [2:25:20<21:42:50, 25.94s/it]\r 10%|███▋                               | 348/3360 [2:25:49<22:18:38, 26.67s/it]\r 10%|███▋                               | 349/3360 [2:26:13<21:39:11, 25.89s/it]\r 10%|███▋                               | 350/3360 [2:26:35<20:38:18, 24.68s/it]\r                                                                                \r{'loss': 1.5498, 'grad_norm': 3.1705737113952637, 'learning_rate': 9.999471159635539e-05, 'epoch': 0.62}\r\n\r 10%|███▋                               | 350/3360 [2:26:35<20:38:18, 24.68s/it]\r 10%|███▋                               | 351/3360 [2:27:02<21:16:21, 25.45s/it]\r 10%|███▋                               | 352/3360 [2:27:28<21:17:49, 25.49s/it]\r 11%|███▋                               | 353/3360 [2:27:55<21:42:49, 26.00s/it]\r 11%|███▋                               | 354/3360 [2:28:21<21:49:30, 26.14s/it]\r 11%|███▋                               | 355/3360 [2:28:46<21:28:39, 25.73s/it]\r 11%|███▋                               | 356/3360 [2:29:12<21:36:27, 25.89s/it]\r 11%|███▋                               | 357/3360 [2:29:38<21:39:03, 25.96s/it]\r 11%|███▋                               | 358/3360 [2:30:05<21:47:20, 26.13s/it]\r 11%|███▋                               | 359/3360 [2:30:30<21:39:16, 25.98s/it]\r 11%|███▊                               | 360/3360 [2:30:54<21:05:49, 25.32s/it]\r                                                                                \r{'loss': 1.5132, 'grad_norm': 2.590669870376587, 'learning_rate': 9.998445910004082e-05, 'epoch': 0.64}\r\n\r 11%|███▊                               | 360/3360 [2:30:54<21:05:49, 25.32s/it]\r 11%|███▊                               | 361/3360 [2:31:23<21:53:02, 26.27s/it]\r 11%|███▊                               | 362/3360 [2:31:48<21:32:07, 25.86s/it]\r 11%|███▊                               | 363/3360 [2:32:08<20:05:50, 24.14s/it]\r 11%|███▊                               | 364/3360 [2:32:36<21:00:40, 25.25s/it]\r 11%|███▊                               | 365/3360 [2:33:04<21:47:43, 26.20s/it]\r 11%|███▊                               | 366/3360 [2:33:35<22:58:20, 27.62s/it]\r 11%|███▊                               | 367/3360 [2:33:59<22:09:37, 26.65s/it]\r 11%|███▊                               | 368/3360 [2:34:29<22:55:24, 27.58s/it]\r 11%|███▊                               | 369/3360 [2:34:54<22:14:45, 26.78s/it]\r 11%|███▊                               | 370/3360 [2:35:20<22:06:40, 26.62s/it]\r                                                                                \r{'loss': 1.703, 'grad_norm': 3.492126703262329, 'learning_rate': 9.996881190417393e-05, 'epoch': 0.66}\r\n\r 11%|███▊                               | 370/3360 [2:35:20<22:06:40, 26.62s/it]\r 11%|███▊                               | 371/3360 [2:35:51<23:01:19, 27.73s/it]\r 11%|███▉                               | 372/3360 [2:36:16<22:29:27, 27.10s/it]\r 11%|███▉                               | 373/3360 [2:36:47<23:20:39, 28.14s/it]\r 11%|███▉                               | 374/3360 [2:37:09<21:46:58, 26.26s/it]\r 11%|███▉                               | 375/3360 [2:37:35<21:54:53, 26.43s/it]\r 11%|███▉                               | 376/3360 [2:38:05<22:36:49, 27.28s/it]\r 11%|███▉                               | 377/3360 [2:38:28<21:32:58, 26.01s/it]\r 11%|███▉                               | 378/3360 [2:38:51<20:48:43, 25.13s/it]\r 11%|███▉                               | 379/3360 [2:39:15<20:31:14, 24.78s/it]\r 11%|███▉                               | 380/3360 [2:39:40<20:35:54, 24.88s/it]\r                                                                                \r{'loss': 1.6165, 'grad_norm': 2.6305856704711914, 'learning_rate': 9.994777169751806e-05, 'epoch': 0.68}\r\n\r 11%|███▉                               | 380/3360 [2:39:40<20:35:54, 24.88s/it]\r 11%|███▉                               | 381/3360 [2:40:03<20:08:14, 24.34s/it]\r 11%|███▉                               | 382/3360 [2:40:31<20:57:54, 25.34s/it]\r 11%|███▉                               | 383/3360 [2:40:56<21:03:03, 25.46s/it]\r 11%|████                               | 384/3360 [2:41:23<21:26:18, 25.93s/it]\r 11%|████                               | 385/3360 [2:41:50<21:30:34, 26.03s/it]\r 11%|████                               | 386/3360 [2:42:12<20:30:14, 24.82s/it]\r 12%|████                               | 387/3360 [2:42:36<20:19:19, 24.61s/it]\r 12%|████                               | 388/3360 [2:42:57<19:32:38, 23.67s/it]\r 12%|████                               | 389/3360 [2:43:19<19:00:57, 23.04s/it]\r 12%|████                               | 390/3360 [2:43:44<19:36:39, 23.77s/it]\r                                                                                \r{'loss': 1.3876, 'grad_norm': 2.812791585922241, 'learning_rate': 9.992134075089084e-05, 'epoch': 0.7}\r\n\r 12%|████                               | 390/3360 [2:43:44<19:36:39, 23.77s/it]\r 12%|████                               | 391/3360 [2:44:09<19:56:05, 24.17s/it]\r 12%|████                               | 392/3360 [2:44:32<19:38:46, 23.83s/it]\r 12%|████                               | 393/3360 [2:44:56<19:34:20, 23.75s/it]\r 12%|████                               | 394/3360 [2:45:22<20:02:35, 24.33s/it]\r 12%|████                               | 395/3360 [2:45:42<19:05:05, 23.17s/it]\r 12%|████▏                              | 396/3360 [2:46:09<19:52:16, 24.14s/it]\r 12%|████▏                              | 397/3360 [2:46:31<19:25:36, 23.60s/it]\r 12%|████▏                              | 398/3360 [2:46:58<20:17:51, 24.67s/it]\r 12%|████▏                              | 399/3360 [2:47:22<20:09:05, 24.50s/it]\r 12%|████▏                              | 400/3360 [2:47:48<20:32:51, 24.99s/it]\r                                                                                \r{'loss': 1.5452, 'grad_norm': 3.2908573150634766, 'learning_rate': 9.988952191691925e-05, 'epoch': 0.71}\r\n\r 12%|████▏                              | 400/3360 [2:47:48<20:32:51, 24.99s/it]\r 12%|████▏                              | 401/3360 [2:48:14<20:35:45, 25.06s/it]\r 12%|████▏                              | 402/3360 [2:48:38<20:27:59, 24.91s/it]\r 12%|████▏                              | 403/3360 [2:49:05<20:56:04, 25.49s/it]\r 12%|████▏                              | 404/3360 [2:49:34<21:47:13, 26.53s/it]\r 12%|████▏                              | 405/3360 [2:50:01<21:51:18, 26.63s/it]\r 12%|████▏                              | 406/3360 [2:50:26<21:33:50, 26.28s/it]\r 12%|████▏                              | 407/3360 [2:50:47<20:18:18, 24.75s/it]\r 12%|████▎                              | 408/3360 [2:51:12<20:10:11, 24.60s/it]\r 12%|████▎                              | 409/3360 [2:51:40<21:04:47, 25.72s/it]\r 12%|████▎                              | 410/3360 [2:52:03<20:27:58, 24.98s/it]\r                                                                                \r{'loss': 1.613, 'grad_norm': 2.7474002838134766, 'learning_rate': 9.985231862973168e-05, 'epoch': 0.73}\r\n\r 12%|████▎                              | 410/3360 [2:52:03<20:27:58, 24.98s/it]\r 12%|████▎                              | 411/3360 [2:52:28<20:24:31, 24.91s/it]\r 12%|████▎                              | 412/3360 [2:52:51<20:02:49, 24.48s/it]\r 12%|████▎                              | 413/3360 [2:53:21<21:22:28, 26.11s/it]\r 12%|████▎                              | 414/3360 [2:53:42<20:03:17, 24.51s/it]\r 12%|████▎                              | 415/3360 [2:54:09<20:35:16, 25.17s/it]\r 12%|████▎                              | 416/3360 [2:54:32<20:10:06, 24.66s/it]\r 12%|████▎                              | 417/3360 [2:54:59<20:39:49, 25.28s/it]\r 12%|████▎                              | 418/3360 [2:55:24<20:33:22, 25.15s/it]\r 12%|████▎                              | 419/3360 [2:55:52<21:21:41, 26.15s/it]\r 12%|████▍                              | 420/3360 [2:56:18<21:08:03, 25.88s/it]\r                                                                                \r{'loss': 1.6223, 'grad_norm': 2.948652744293213, 'learning_rate': 9.980973490458728e-05, 'epoch': 0.75}\r\n\r 12%|████▍                              | 420/3360 [2:56:18<21:08:03, 25.88s/it]\r 13%|████▍                              | 421/3360 [2:56:47<21:54:33, 26.84s/it]\r 13%|████▍                              | 422/3360 [2:57:16<22:30:59, 27.59s/it]\r 13%|████▍                              | 423/3360 [2:57:45<22:54:23, 28.08s/it]\r 13%|████▍                              | 424/3360 [2:58:08<21:40:56, 26.59s/it]\r 13%|████▍                              | 425/3360 [2:58:33<21:09:01, 25.94s/it]\r 13%|████▍                              | 426/3360 [2:58:59<21:09:41, 25.97s/it]\r 13%|████▍                              | 427/3360 [2:59:20<20:04:20, 24.64s/it]\r 13%|████▍                              | 428/3360 [2:59:46<20:14:20, 24.85s/it]\r 13%|████▍                              | 429/3360 [3:00:06<18:59:58, 23.34s/it]\r 13%|████▍                              | 430/3360 [3:00:30<19:13:22, 23.62s/it]\r                                                                                \r{'loss': 1.5303, 'grad_norm': 4.351890563964844, 'learning_rate': 9.976177533744261e-05, 'epoch': 0.77}\r\n\r 13%|████▍                              | 430/3360 [3:00:30<19:13:22, 23.62s/it]\r 13%|████▍                              | 431/3360 [3:00:53<19:01:15, 23.38s/it]\r 13%|████▌                              | 432/3360 [3:01:15<18:41:05, 22.97s/it]\r 13%|████▌                              | 433/3360 [3:01:41<19:22:41, 23.83s/it]\r 13%|████▌                              | 434/3360 [3:02:07<19:56:17, 24.53s/it]\r 13%|████▌                              | 435/3360 [3:02:29<19:20:42, 23.81s/it]\r 13%|████▌                              | 436/3360 [3:02:54<19:41:07, 24.24s/it]\r 13%|████▌                              | 437/3360 [3:03:19<19:57:00, 24.57s/it]\r 13%|████▌                              | 438/3360 [3:03:42<19:29:52, 24.02s/it]\r 13%|████▌                              | 439/3360 [3:04:13<21:10:26, 26.10s/it]\r 13%|████▌                              | 440/3360 [3:04:36<20:29:42, 25.27s/it]\r                                                                                \r{'loss': 1.5474, 'grad_norm': 4.548303604125977, 'learning_rate': 9.97084451044556e-05, 'epoch': 0.79}\r\n\r 13%|████▌                              | 440/3360 [3:04:36<20:29:42, 25.27s/it]\r 13%|████▌                              | 441/3360 [3:05:02<20:33:37, 25.36s/it]\r 13%|████▌                              | 442/3360 [3:05:26<20:14:48, 24.98s/it]\r 13%|████▌                              | 443/3360 [3:05:50<20:03:36, 24.76s/it]\r 13%|████▋                              | 444/3360 [3:06:19<21:03:12, 25.99s/it]\r 13%|████▋                              | 445/3360 [3:06:43<20:31:19, 25.34s/it]\r 13%|████▋                              | 446/3360 [3:07:03<19:07:15, 23.62s/it]\r 13%|████▋                              | 447/3360 [3:07:25<18:41:53, 23.11s/it]\r 13%|████▋                              | 448/3360 [3:07:50<19:19:01, 23.88s/it]\r 13%|████▋                              | 449/3360 [3:08:15<19:36:42, 24.25s/it]\r 13%|████▋                              | 450/3360 [3:08:44<20:45:31, 25.68s/it]\r                                                                                \r{'loss': 1.4864, 'grad_norm': 2.562734365463257, 'learning_rate': 9.964974996142698e-05, 'epoch': 0.8}\r\n\r 13%|████▋                              | 450/3360 [3:08:44<20:45:31, 25.68s/it]\r 13%|████▋                              | 451/3360 [3:09:11<20:56:40, 25.92s/it]\r 13%|████▋                              | 452/3360 [3:09:33<19:56:42, 24.69s/it]\r 13%|████▋                              | 453/3360 [3:09:57<19:45:47, 24.47s/it]\r 14%|████▋                              | 454/3360 [3:10:22<20:01:50, 24.81s/it]\r 14%|████▋                              | 455/3360 [3:10:50<20:41:56, 25.65s/it]\r 14%|████▊                              | 456/3360 [3:11:16<20:42:39, 25.67s/it]\r 14%|████▊                              | 457/3360 [3:11:40<20:23:16, 25.28s/it]\r 14%|████▊                              | 458/3360 [3:12:04<20:08:38, 24.99s/it]\r 14%|████▊                              | 459/3360 [3:12:29<20:10:10, 25.03s/it]\r 14%|████▊                              | 460/3360 [3:12:55<20:19:44, 25.24s/it]\r                                                                                \r{'loss': 1.5383, 'grad_norm': 2.8942601680755615, 'learning_rate': 9.958569624317893e-05, 'epoch': 0.82}\r\n\r 14%|████▊                              | 460/3360 [3:12:55<20:19:44, 25.24s/it]\r 14%|████▊                              | 461/3360 [3:13:15<19:05:40, 23.71s/it]\r 14%|████▊                              | 462/3360 [3:13:44<20:19:55, 25.26s/it]\r 14%|████▊                              | 463/3360 [3:14:08<20:02:31, 24.91s/it]\r 14%|████▊                              | 464/3360 [3:14:35<20:26:34, 25.41s/it]\r 14%|████▊                              | 465/3360 [3:14:59<20:09:12, 25.06s/it]\r 14%|████▊                              | 466/3360 [3:15:26<20:37:46, 25.66s/it]\r 14%|████▊                              | 467/3360 [3:15:52<20:38:04, 25.68s/it]\r 14%|████▉                              | 468/3360 [3:16:16<20:09:48, 25.10s/it]\r 14%|████▉                              | 469/3360 [3:16:40<20:03:28, 24.98s/it]\r 14%|████▉                              | 470/3360 [3:17:06<20:19:39, 25.32s/it]\r                                                                                \r{'loss': 1.6424, 'grad_norm': 5.147312164306641, 'learning_rate': 9.951629086287151e-05, 'epoch': 0.84}\r\n\r 14%|████▉                              | 470/3360 [3:17:06<20:19:39, 25.32s/it]\r 14%|████▉                              | 471/3360 [3:17:34<20:51:02, 25.98s/it]\r 14%|████▉                              | 472/3360 [3:17:59<20:37:39, 25.71s/it]\r 14%|████▉                              | 473/3360 [3:18:24<20:30:22, 25.57s/it]\r 14%|████▉                              | 474/3360 [3:18:46<19:31:44, 24.36s/it]\r 14%|████▉                              | 475/3360 [3:19:13<20:18:21, 25.34s/it]\r 14%|████▉                              | 476/3360 [3:19:40<20:40:32, 25.81s/it]\r 14%|████▉                              | 477/3360 [3:20:02<19:44:59, 24.66s/it]\r 14%|████▉                              | 478/3360 [3:20:29<20:14:26, 25.28s/it]\r 14%|████▉                              | 479/3360 [3:20:52<19:44:52, 24.68s/it]\r 14%|█████                              | 480/3360 [3:21:16<19:35:38, 24.49s/it]\r                                                                                \r{'loss': 1.5663, 'grad_norm': 3.9685349464416504, 'learning_rate': 9.944154131125642e-05, 'epoch': 0.86}\r\n\r 14%|█████                              | 480/3360 [3:21:16<19:35:38, 24.49s/it]\r 14%|█████                              | 481/3360 [3:21:39<19:15:21, 24.08s/it]\r 14%|█████                              | 482/3360 [3:22:10<20:52:36, 26.11s/it]\r 14%|█████                              | 483/3360 [3:22:34<20:16:33, 25.37s/it]\r 14%|█████                              | 484/3360 [3:22:58<20:01:51, 25.07s/it]\r 14%|█████                              | 485/3360 [3:23:22<19:42:30, 24.68s/it]\r 14%|█████                              | 486/3360 [3:23:45<19:16:03, 24.13s/it]\r 14%|█████                              | 487/3360 [3:24:11<19:38:57, 24.62s/it]\r 15%|█████                              | 488/3360 [3:24:35<19:41:07, 24.68s/it]\r 15%|█████                              | 489/3360 [3:25:00<19:33:15, 24.52s/it]\r 15%|█████                              | 490/3360 [3:25:25<19:43:03, 24.73s/it]\r                                                                                \r{'loss': 1.5996, 'grad_norm': 2.914736270904541, 'learning_rate': 9.936145565586871e-05, 'epoch': 0.87}\r\n\r 15%|█████                              | 490/3360 [3:25:25<19:43:03, 24.73s/it]\r 15%|█████                              | 491/3360 [3:25:50<19:55:36, 25.00s/it]\r 15%|█████▏                             | 492/3360 [3:26:14<19:33:14, 24.54s/it]\r 15%|█████▏                             | 493/3360 [3:26:42<20:20:18, 25.54s/it]\r 15%|█████▏                             | 494/3360 [3:27:03<19:23:41, 24.36s/it]\r 15%|█████▏                             | 495/3360 [3:27:32<20:30:32, 25.77s/it]\r 15%|█████▏                             | 496/3360 [3:27:57<20:15:46, 25.47s/it]\r 15%|█████▏                             | 497/3360 [3:28:20<19:33:27, 24.59s/it]\r 15%|█████▏                             | 498/3360 [3:28:49<20:33:10, 25.85s/it]\r 15%|█████▏                             | 499/3360 [3:29:12<19:53:13, 25.02s/it]\r 15%|█████▏                             | 500/3360 [3:29:37<20:03:51, 25.26s/it]\r                                                                                \r{'loss': 1.7262, 'grad_norm': 4.308140754699707, 'learning_rate': 9.927604254015585e-05, 'epoch': 0.89}\r\n\r 15%|█████▏                             | 500/3360 [3:29:37<20:03:51, 25.26s/it]\r 15%|█████▏                             | 501/3360 [3:30:01<19:32:43, 24.61s/it]\r 15%|█████▏                             | 502/3360 [3:30:26<19:39:31, 24.76s/it]\r 15%|█████▏                             | 503/3360 [3:30:52<20:04:09, 25.29s/it]\r 15%|█████▎                             | 504/3360 [3:31:14<19:10:56, 24.18s/it]\r 15%|█████▎                             | 505/3360 [3:31:44<20:36:22, 25.98s/it]\r 15%|█████▎                             | 506/3360 [3:32:08<20:08:12, 25.40s/it]\r 15%|█████▎                             | 507/3360 [3:32:31<19:36:26, 24.74s/it]\r 15%|█████▎                             | 508/3360 [3:32:56<19:34:51, 24.72s/it]\r 15%|█████▎                             | 509/3360 [3:33:18<19:03:14, 24.06s/it]\r 15%|█████▎                             | 510/3360 [3:33:48<20:15:47, 25.60s/it]\r                                                                                \r{'loss': 1.7067, 'grad_norm': 3.621767282485962, 'learning_rate': 9.918531118254507e-05, 'epoch': 0.91}\r\n\r 15%|█████▎                             | 510/3360 [3:33:48<20:15:47, 25.60s/it]\r 15%|█████▎                             | 511/3360 [3:34:09<19:11:10, 24.24s/it]\r 15%|█████▎                             | 512/3360 [3:34:36<20:01:12, 25.31s/it]\r 15%|█████▎                             | 513/3360 [3:35:02<20:06:22, 25.42s/it]"
+      "Current Directory:\r\n/Workspace/Users/donghao.huang@mastercard.com/llm-finetuning/llama-factory\r\nconfig/llama3_8b_lora_sft.yaml:\r\n {\r\n  \"model_name_or_path\": \"gradientai/Llama-3-8B-Instruct-Gradient-1048k\",\r\n  \"stage\": \"sft\",\r\n  \"do_train\": true,\r\n  \"finetuning_type\": \"lora\",\r\n  \"lora_target\": \"all\",\r\n  \"quantization_bit\": 4,\r\n  \"loraplus_lr_ratio\": 16.0,\r\n  \"dataset\": \"alpaca_mac\",\r\n  \"template\": \"llama3\",\r\n  \"cutoff_len\": 1024,\r\n  \"max_samples\": 4528,\r\n  \"overwrite_cache\": true,\r\n  \"preprocessing_num_workers\": 16,\r\n  \"output_dir\": \"/Workspace/Users/donghao.huang@mastercard.com/lf-saves/llama3-8b/lora/sft/\",\r\n  \"logging_steps\": 10,\r\n  \"save_steps\": 560,\r\n  \"plot_loss\": true,\r\n  \"overwrite_output_dir\": true,\r\n  \"per_device_train_batch_size\": 1,\r\n  \"gradient_accumulation_steps\": 8,\r\n  \"learning_rate\": 0.0001,\r\n  \"num_train_epochs\": 6.0,\r\n  \"lr_scheduler_type\": \"cosine\",\r\n  \"warmup_ratio\": 0.1,\r\n  \"bf16\": true,\r\n  \"ddp_timeout\": 180000000,\r\n  \"val_size\": 0.01,\r\n  \"per_device_eval_batch_size\": 1,\r\n  \"eval_strategy\": \"steps\",\r\n  \"eval_steps\": 560,\r\n  \"report_to\": \"none\"\r\n}\r\n2024-07-06 05:25:57.983661: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\r\nTo enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\r\n[2024-07-06 05:26:07,672] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n07/06/2024 05:26:16 - WARNING - llamafactory.hparams.parser - We recommend enable `upcast_layernorm` in quantized training.\r\n07/06/2024 05:26:16 - INFO - llamafactory.hparams.parser - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:26:16,583 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/tokenizer.json\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:26:16,583 >> loading file added_tokens.json from cache at None\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:26:16,583 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/special_tokens_map.json\r\n[INFO|tokenization_utils_base.py:2161] 2024-07-06 05:26:16,583 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/tokenizer_config.json\r\n[WARNING|logging.py:313] 2024-07-06 05:26:16,885 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\r\n07/06/2024 05:26:16 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>\r\n07/06/2024 05:26:16 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>\r\n07/06/2024 05:26:17 - INFO - llamafactory.data.loader - Loading dataset alpaca_mac.json...\r\n\rConverting format of dataset (num_proc=16):   0%| | 0/4528 [00:00<?, ? examples/\rConverting format of dataset (num_proc=16):  81%|▊| 3679/4528 [00:00<00:00, 3628\rConverting format of dataset (num_proc=16): 100%|█| 4528/4528 [00:00<00:00, 2384\r\n\rRunning tokenizer on dataset (num_proc=16):   0%| | 0/4528 [00:00<?, ? examples/\rRunning tokenizer on dataset (num_proc=16):   6%| | 283/4528 [00:00<00:08, 481.9\rRunning tokenizer on dataset (num_proc=16):  12%|▏| 566/4528 [00:00<00:04, 876.9\rRunning tokenizer on dataset (num_proc=16):  19%|▏| 849/4528 [00:00<00:03, 1198.\rRunning tokenizer on dataset (num_proc=16):  25%|▎| 1132/4528 [00:01<00:03, 1124\rRunning tokenizer on dataset (num_proc=16):  31%|▎| 1415/4528 [00:01<00:02, 1298\rRunning tokenizer on dataset (num_proc=16):  44%|▍| 1981/4528 [00:01<00:01, 1907\rRunning tokenizer on dataset (num_proc=16):  50%|▌| 2264/4528 [00:01<00:01, 1943\rRunning tokenizer on dataset (num_proc=16):  56%|▌| 2547/4528 [00:01<00:01, 1887\rRunning tokenizer on dataset (num_proc=16):  62%|▋| 2830/4528 [00:01<00:00, 1852\rRunning tokenizer on dataset (num_proc=16):  69%|▋| 3113/4528 [00:02<00:00, 1795\rRunning tokenizer on dataset (num_proc=16):  75%|▊| 3396/4528 [00:02<00:00, 1785\rRunning tokenizer on dataset (num_proc=16):  81%|▊| 3679/4528 [00:02<00:00, 1789\rRunning tokenizer on dataset (num_proc=16):  94%|▉| 4245/4528 [00:02<00:00, 2014\rRunning tokenizer on dataset (num_proc=16): 100%|█| 4528/4528 [00:02<00:00, 1948\rRunning tokenizer on dataset (num_proc=16): 100%|█| 4528/4528 [00:02<00:00, 1571\r\ninput_ids:\r\n[128000, 128006, 882, 128007, 271, 5618, 15025, 279, 2768, 8620, 1495, 1139, 6498, 323, 3493, 1193, 279, 25548, 2262, 11, 4400, 775, 627, 37087, 6271, 245, 100815, 121991, 110139, 113265, 108057, 1811, 128009, 128006, 78191, 128007, 271, 18433, 358, 574, 2682, 555, 264, 39935, 45586, 13, 128009]\r\ninputs:\r\n<|begin_of_text|><|start_header_id|>user<|end_header_id|>\r\n\r\nPlease translate the following Chinese text into English and provide only the translated content, nothing else.\r\n全仗着狐仙搭救。<|eot_id|><|start_header_id|>assistant<|end_header_id|>\r\n\r\nBecause I was protected by a fox fairy.<|eot_id|>\r\nlabel_ids:\r\n[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 18433, 358, 574, 2682, 555, 264, 39935, 45586, 13, 128009]\r\nlabels:\r\nBecause I was protected by a fox fairy.<|eot_id|>\r\n[INFO|configuration_utils.py:733] 2024-07-06 05:26:21,331 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/config.json\r\n[INFO|configuration_utils.py:800] 2024-07-06 05:26:21,332 >> Model config LlamaConfig {\r\n  \"_name_or_path\": \"gradientai/Llama-3-8B-Instruct-Gradient-1048k\",\r\n  \"architectures\": [\r\n    \"LlamaForCausalLM\"\r\n  ],\r\n  \"attention_bias\": false,\r\n  \"attention_dropout\": 0.0,\r\n  \"bos_token_id\": 128000,\r\n  \"eos_token_id\": 128001,\r\n  \"hidden_act\": \"silu\",\r\n  \"hidden_size\": 4096,\r\n  \"initializer_range\": 0.02,\r\n  \"intermediate_size\": 14336,\r\n  \"max_position_embeddings\": 1048576,\r\n  \"mlp_bias\": false,\r\n  \"model_type\": \"llama\",\r\n  \"num_attention_heads\": 32,\r\n  \"num_hidden_layers\": 32,\r\n  \"num_key_value_heads\": 8,\r\n  \"pretraining_tp\": 1,\r\n  \"rms_norm_eps\": 1e-05,\r\n  \"rope_scaling\": null,\r\n  \"rope_theta\": 3580165449.0,\r\n  \"tie_word_embeddings\": false,\r\n  \"torch_dtype\": \"bfloat16\",\r\n  \"transformers_version\": \"4.42.3\",\r\n  \"use_cache\": true,\r\n  \"vocab_size\": 128256\r\n}\r\n\r\n07/06/2024 05:26:21 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit with bitsandbytes.\r\n[INFO|modeling_utils.py:3556] 2024-07-06 05:26:21,358 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/model.safetensors.index.json\r\n[INFO|modeling_utils.py:1531] 2024-07-06 05:26:21,360 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.\r\n[INFO|configuration_utils.py:1000] 2024-07-06 05:26:21,361 >> Generate config GenerationConfig {\r\n  \"bos_token_id\": 128000,\r\n  \"eos_token_id\": 128001\r\n}\r\n\r\n\rLoading checkpoint shards:   0%|                          | 0/4 [00:00<?, ?it/s]\rLoading checkpoint shards:  25%|████▌             | 1/4 [00:01<00:03,  1.20s/it]\rLoading checkpoint shards:  50%|█████████         | 2/4 [00:02<00:02,  1.15s/it]\rLoading checkpoint shards:  75%|█████████████▌    | 3/4 [00:03<00:01,  1.13s/it]\rLoading checkpoint shards: 100%|██████████████████| 4/4 [00:03<00:00,  1.16it/s]\rLoading checkpoint shards: 100%|██████████████████| 4/4 [00:03<00:00,  1.03it/s]\r\n[INFO|modeling_utils.py:4364] 2024-07-06 05:26:25,528 >> All model checkpoint weights were used when initializing LlamaForCausalLM.\r\n\r\n[INFO|modeling_utils.py:4372] 2024-07-06 05:26:25,528 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at gradientai/Llama-3-8B-Instruct-Gradient-1048k.\r\nIf your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.\r\n[INFO|configuration_utils.py:955] 2024-07-06 05:26:25,553 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--gradientai--Llama-3-8B-Instruct-Gradient-1048k/snapshots/8697fb25cb77c852311e03b4464b8467471d56a4/generation_config.json\r\n[INFO|configuration_utils.py:1000] 2024-07-06 05:26:25,553 >> Generate config GenerationConfig {\r\n  \"bos_token_id\": 128000,\r\n  \"do_sample\": true,\r\n  \"eos_token_id\": [\r\n    128001,\r\n    128009\r\n  ],\r\n  \"max_length\": 4096,\r\n  \"temperature\": 0.6,\r\n  \"top_p\": 0.9\r\n}\r\n\r\n07/06/2024 05:26:25 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.\r\n07/06/2024 05:26:25 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.\r\n07/06/2024 05:26:25 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.\r\n07/06/2024 05:26:25 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA\r\n07/06/2024 05:26:25 - INFO - llamafactory.model.model_utils.misc - Found linear modules: gate_proj,v_proj,o_proj,k_proj,up_proj,down_proj,q_proj\r\n07/06/2024 05:26:26 - INFO - llamafactory.model.loader - trainable params: 20,971,520 || all params: 8,051,232,768 || trainable%: 0.2605\r\n[INFO|trainer.py:642] 2024-07-06 05:26:26,145 >> Using auto half precision backend\r\n07/06/2024 05:26:26 - WARNING - llamafactory.train.callbacks - Previous trainer log in this folder will be deleted.\r\ntraining_args.resume_from_checkpoint: None\r\n07/06/2024 05:26:26 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.\r\n[INFO|trainer.py:2128] 2024-07-06 05:26:26,821 >> ***** Running training *****\r\n[INFO|trainer.py:2129] 2024-07-06 05:26:26,821 >>   Num examples = 4,482\r\n[INFO|trainer.py:2130] 2024-07-06 05:26:26,821 >>   Num Epochs = 6\r\n[INFO|trainer.py:2131] 2024-07-06 05:26:26,821 >>   Instantaneous batch size per device = 1\r\n[INFO|trainer.py:2134] 2024-07-06 05:26:26,821 >>   Total train batch size (w. parallel, distributed & accumulation) = 8\r\n[INFO|trainer.py:2135] 2024-07-06 05:26:26,821 >>   Gradient Accumulation steps = 8\r\n[INFO|trainer.py:2136] 2024-07-06 05:26:26,821 >>   Total optimization steps = 3,360\r\n[INFO|trainer.py:2137] 2024-07-06 05:26:26,825 >>   Number of trainable parameters = 20,971,520\r\n\r  0%|                                                  | 0/3360 [00:00<?, ?it/s]\r  0%|                                       | 1/3360 [00:26<24:56:16, 26.73s/it]\r  0%|                                       | 2/3360 [00:54<25:38:57, 27.50s/it]\r  0%|                                       | 3/3360 [01:19<24:28:42, 26.25s/it]\r  0%|                                       | 4/3360 [01:40<22:24:16, 24.03s/it]\r  0%|                                       | 5/3360 [02:10<24:25:52, 26.22s/it]\r  0%|                                       | 6/3360 [02:38<25:05:31, 26.93s/it]\r  0%|                                       | 7/3360 [03:02<24:12:17, 25.99s/it]\r  0%|                                       | 8/3360 [03:27<23:49:00, 25.58s/it]\r  0%|                                       | 9/3360 [03:54<24:16:12, 26.07s/it]\r  0%|                                      | 10/3360 [04:21<24:38:04, 26.47s/it]\r                                                                                \r{'loss': 2.2828, 'grad_norm': 1.950901985168457, 'learning_rate': 2.9761904761904763e-06, 'epoch': 0.02}\r\n\r  0%|                                      | 10/3360 [04:21<24:38:04, 26.47s/it]\r  0%|                                      | 11/3360 [04:48<24:35:43, 26.44s/it]\r  0%|▏                                     | 12/3360 [05:14<24:37:20, 26.48s/it]\r  0%|▏                                     | 13/3360 [05:38<23:46:55, 25.58s/it]\r  0%|▏                                     | 14/3360 [06:03<23:45:55, 25.57s/it]\r  0%|▏                                     | 15/3360 [06:28<23:35:00, 25.38s/it]\r  0%|▏                                     | 16/3360 [06:59<24:56:43, 26.86s/it]\r  1%|▏                                     | 17/3360 [07:22<23:58:05, 25.81s/it]\r  1%|▏                                     | 18/3360 [07:46<23:33:14, 25.37s/it]\r  1%|▏                                     | 19/3360 [08:14<24:09:48, 26.04s/it]\r  1%|▏                                     | 20/3360 [08:37<23:27:39, 25.29s/it]\r                                                                                \r{'loss': 2.1958, 'grad_norm': 2.308849334716797, 'learning_rate': 5.9523809523809525e-06, 'epoch': 0.04}\r\n\r  1%|▏                                     | 20/3360 [08:37<23:27:39, 25.29s/it]\r  1%|▏                                     | 21/3360 [09:04<23:51:12, 25.72s/it]\r  1%|▏                                     | 22/3360 [09:27<23:06:18, 24.92s/it]\r  1%|▎                                     | 23/3360 [09:50<22:26:55, 24.22s/it]\r  1%|▎                                     | 24/3360 [10:15<22:37:56, 24.42s/it]\r  1%|▎                                     | 25/3360 [10:35<21:31:10, 23.23s/it]\r  1%|▎                                     | 26/3360 [10:58<21:20:38, 23.05s/it]\r  1%|▎                                     | 27/3360 [11:25<22:35:55, 24.41s/it]\r  1%|▎                                     | 28/3360 [11:55<23:58:46, 25.91s/it]\r  1%|▎                                     | 29/3360 [12:18<23:10:34, 25.05s/it]\r  1%|▎                                     | 30/3360 [12:44<23:34:55, 25.49s/it]\r                                                                                \r{'loss': 1.8784, 'grad_norm': 1.3710776567459106, 'learning_rate': 8.92857142857143e-06, 'epoch': 0.05}\r\n\r  1%|▎                                     | 30/3360 [12:44<23:34:55, 25.49s/it]\r  1%|▎                                     | 31/3360 [13:06<22:33:04, 24.39s/it]\r  1%|▎                                     | 32/3360 [13:28<21:51:00, 23.64s/it]\r  1%|▎                                     | 33/3360 [13:49<21:01:41, 22.75s/it]\r  1%|▍                                     | 34/3360 [14:13<21:26:33, 23.21s/it]\r  1%|▍                                     | 35/3360 [14:39<22:09:10, 23.99s/it]\r  1%|▍                                     | 36/3360 [15:02<21:55:29, 23.75s/it]\r  1%|▍                                     | 37/3360 [15:27<22:17:51, 24.16s/it]\r  1%|▍                                     | 38/3360 [15:50<21:54:20, 23.74s/it]\r  1%|▍                                     | 39/3360 [16:15<22:20:26, 24.22s/it]\r  1%|▍                                     | 40/3360 [16:37<21:35:46, 23.42s/it]\r                                                                                \r{'loss': 1.7298, 'grad_norm': 3.4520955085754395, 'learning_rate': 1.1904761904761905e-05, 'epoch': 0.07}\r\n\r  1%|▍                                     | 40/3360 [16:37<21:35:46, 23.42s/it]\r  1%|▍                                     | 41/3360 [17:03<22:20:43, 24.24s/it]\r  1%|▍                                     | 42/3360 [17:30<23:06:08, 25.07s/it]\r  1%|▍                                     | 43/3360 [17:56<23:22:55, 25.38s/it]\r  1%|▍                                     | 44/3360 [18:19<22:49:24, 24.78s/it]\r  1%|▌                                     | 45/3360 [18:44<22:39:51, 24.61s/it]\r  1%|▌                                     | 46/3360 [19:10<23:02:19, 25.03s/it]\r  1%|▌                                     | 47/3360 [19:39<24:16:30, 26.38s/it]\r  1%|▌                                     | 48/3360 [20:03<23:40:13, 25.73s/it]\r  1%|▌                                     | 49/3360 [20:30<23:52:44, 25.96s/it]\r  1%|▌                                     | 50/3360 [20:57<24:08:40, 26.26s/it]\r                                                                                \r{'loss': 1.8498, 'grad_norm': 1.293561577796936, 'learning_rate': 1.4880952380952381e-05, 'epoch': 0.09}\r\n\r  1%|▌                                     | 50/3360 [20:57<24:08:40, 26.26s/it]\r  2%|▌                                     | 51/3360 [21:24<24:24:51, 26.56s/it]\r  2%|▌                                     | 52/3360 [21:46<23:00:36, 25.04s/it]\r  2%|▌                                     | 53/3360 [22:10<22:50:07, 24.86s/it]\r  2%|▌                                     | 54/3360 [22:36<23:06:20, 25.16s/it]\r  2%|▌                                     | 55/3360 [22:59<22:37:44, 24.65s/it]\r  2%|▋                                     | 56/3360 [23:26<23:07:51, 25.20s/it]\r  2%|▋                                     | 57/3360 [23:50<22:48:16, 24.86s/it]\r  2%|▋                                     | 58/3360 [24:10<21:38:17, 23.59s/it]\r  2%|▋                                     | 59/3360 [24:39<22:59:38, 25.08s/it]\r  2%|▋                                     | 60/3360 [25:04<23:00:50, 25.11s/it]\r                                                                                \r{'loss': 1.6822, 'grad_norm': 2.2295732498168945, 'learning_rate': 1.785714285714286e-05, 'epoch': 0.11}\r\n\r  2%|▋                                     | 60/3360 [25:04<23:00:50, 25.11s/it]\r  2%|▋                                     | 61/3360 [25:31<23:28:37, 25.62s/it]\r  2%|▋                                     | 62/3360 [25:59<24:08:17, 26.35s/it]\r  2%|▋                                     | 63/3360 [26:21<22:59:50, 25.11s/it]\r  2%|▋                                     | 64/3360 [26:47<23:16:38, 25.42s/it]\r  2%|▋                                     | 65/3360 [27:11<22:46:22, 24.88s/it]\r  2%|▋                                     | 66/3360 [27:36<22:49:59, 24.95s/it]\r  2%|▊                                     | 67/3360 [27:59<22:15:10, 24.33s/it]\r  2%|▊                                     | 68/3360 [28:23<22:02:11, 24.10s/it]\r  2%|▊                                     | 69/3360 [28:49<22:39:48, 24.79s/it]\r  2%|▊                                     | 70/3360 [29:14<22:36:35, 24.74s/it]\r                                                                                \r{'loss': 1.7621, 'grad_norm': 1.627418041229248, 'learning_rate': 2.0833333333333336e-05, 'epoch': 0.12}\r\n\r  2%|▊                                     | 70/3360 [29:14<22:36:35, 24.74s/it]\r  2%|▊                                     | 71/3360 [29:37<22:17:54, 24.41s/it]\r  2%|▊                                     | 72/3360 [30:02<22:23:44, 24.52s/it]\r  2%|▊                                     | 73/3360 [30:30<23:12:53, 25.43s/it]\r  2%|▊                                     | 74/3360 [30:57<23:39:53, 25.93s/it]\r  2%|▊                                     | 75/3360 [31:27<24:43:33, 27.10s/it]\r  2%|▊                                     | 76/3360 [31:50<23:36:06, 25.87s/it]\r  2%|▊                                     | 77/3360 [32:18<24:15:04, 26.59s/it]\r  2%|▉                                     | 78/3360 [32:44<24:07:18, 26.46s/it]\r  2%|▉                                     | 79/3360 [33:15<25:16:26, 27.73s/it]\r  2%|▉                                     | 80/3360 [33:38<24:11:10, 26.55s/it]\r                                                                                \r{'loss': 1.6161, 'grad_norm': 1.4014948606491089, 'learning_rate': 2.380952380952381e-05, 'epoch': 0.14}\r\n\r  2%|▉                                     | 80/3360 [33:38<24:11:10, 26.55s/it]\r  2%|▉                                     | 81/3360 [34:04<23:47:56, 26.13s/it]\r  2%|▉                                     | 82/3360 [34:27<23:02:59, 25.31s/it]\r  2%|▉                                     | 83/3360 [34:51<22:34:09, 24.79s/it]\r  2%|▉                                     | 84/3360 [35:13<21:58:04, 24.14s/it]\r  3%|▉                                     | 85/3360 [35:39<22:17:06, 24.50s/it]\r  3%|▉                                     | 86/3360 [36:05<22:44:40, 25.01s/it]\r  3%|▉                                     | 87/3360 [36:31<23:03:13, 25.36s/it]\r  3%|▉                                     | 88/3360 [36:58<23:37:23, 25.99s/it]\r  3%|█                                     | 89/3360 [37:24<23:24:38, 25.77s/it]\r  3%|█                                     | 90/3360 [37:50<23:42:21, 26.10s/it]\r                                                                                \r{'loss': 1.7168, 'grad_norm': 2.215449094772339, 'learning_rate': 2.6785714285714288e-05, 'epoch': 0.16}\r\n\r  3%|█                                     | 90/3360 [37:50<23:42:21, 26.10s/it]\r  3%|█                                     | 91/3360 [38:17<23:48:37, 26.22s/it]\r  3%|█                                     | 92/3360 [38:43<23:48:34, 26.23s/it]\r  3%|█                                     | 93/3360 [39:10<24:05:09, 26.54s/it]\r  3%|█                                     | 94/3360 [39:41<25:13:14, 27.80s/it]\r  3%|█                                     | 95/3360 [40:06<24:22:00, 26.87s/it]\r  3%|█                                     | 96/3360 [40:28<23:00:32, 25.38s/it]\r  3%|█                                     | 97/3360 [40:51<22:28:13, 24.79s/it]\r  3%|█                                     | 98/3360 [41:15<22:14:27, 24.55s/it]\r  3%|█                                     | 99/3360 [41:38<21:51:05, 24.12s/it]\r  3%|█                                    | 100/3360 [42:05<22:25:59, 24.77s/it]\r                                                                                \r{'loss': 1.6314, 'grad_norm': 1.435763955116272, 'learning_rate': 2.9761904761904762e-05, 'epoch': 0.18}\r\n\r  3%|█                                    | 100/3360 [42:05<22:25:59, 24.77s/it]\r  3%|█                                    | 101/3360 [42:29<22:23:14, 24.73s/it]\r  3%|█                                    | 102/3360 [42:52<21:46:25, 24.06s/it]\r  3%|█▏                                   | 103/3360 [43:15<21:31:09, 23.79s/it]\r  3%|█▏                                   | 104/3360 [43:37<21:08:22, 23.37s/it]\r  3%|█▏                                   | 105/3360 [44:06<22:41:31, 25.10s/it]\r  3%|█▏                                   | 106/3360 [44:34<23:17:17, 25.76s/it]\r  3%|█▏                                   | 107/3360 [44:56<22:19:18, 24.70s/it]\r  3%|█▏                                   | 108/3360 [45:22<22:38:47, 25.07s/it]\r  3%|█▏                                   | 109/3360 [45:48<22:46:52, 25.23s/it]\r  3%|█▏                                   | 110/3360 [46:14<22:59:37, 25.47s/it]\r                                                                                \r{'loss': 1.6137, 'grad_norm': 1.5036354064941406, 'learning_rate': 3.273809523809524e-05, 'epoch': 0.2}\r\n\r  3%|█▏                                   | 110/3360 [46:14<22:59:37, 25.47s/it]\r  3%|█▏                                   | 111/3360 [46:38<22:49:02, 25.28s/it]\r  3%|█▏                                   | 112/3360 [47:04<22:51:44, 25.34s/it]\r  3%|█▏                                   | 113/3360 [47:27<22:15:21, 24.68s/it]\r  3%|█▎                                   | 114/3360 [47:50<21:45:12, 24.13s/it]\r  3%|█▎                                   | 115/3360 [48:13<21:33:21, 23.91s/it]\r  3%|█▎                                   | 116/3360 [48:40<22:11:57, 24.64s/it]\r  3%|█▎                                   | 117/3360 [49:05<22:22:04, 24.83s/it]\r  4%|█▎                                   | 118/3360 [49:33<23:14:20, 25.81s/it]\r  4%|█▎                                   | 119/3360 [49:55<22:14:43, 24.71s/it]\r  4%|█▎                                   | 120/3360 [50:28<24:21:25, 27.06s/it]\r                                                                                \r{'loss': 1.6265, 'grad_norm': 1.6486930847167969, 'learning_rate': 3.571428571428572e-05, 'epoch': 0.21}\r\n\r  4%|█▎                                   | 120/3360 [50:28<24:21:25, 27.06s/it]\r  4%|█▎                                   | 121/3360 [50:53<23:45:18, 26.40s/it]\r  4%|█▎                                   | 122/3360 [51:14<22:27:17, 24.97s/it]\r  4%|█▎                                   | 123/3360 [51:37<21:55:53, 24.39s/it]\r  4%|█▎                                   | 124/3360 [52:00<21:34:32, 24.00s/it]\r  4%|█▍                                   | 125/3360 [52:25<21:40:21, 24.12s/it]\r  4%|█▍                                   | 126/3360 [52:54<23:10:29, 25.80s/it]\r  4%|█▍                                   | 127/3360 [53:21<23:18:52, 25.96s/it]\r  4%|█▍                                   | 128/3360 [53:48<23:40:25, 26.37s/it]\r  4%|█▍                                   | 129/3360 [54:10<22:21:16, 24.91s/it]\r  4%|█▍                                   | 130/3360 [54:37<23:09:33, 25.81s/it]\r                                                                                \r{'loss': 1.6258, 'grad_norm': 2.645925521850586, 'learning_rate': 3.8690476190476195e-05, 'epoch': 0.23}\r\n\r  4%|█▍                                   | 130/3360 [54:37<23:09:33, 25.81s/it]\r  4%|█▍                                   | 131/3360 [55:04<23:24:26, 26.10s/it]\r  4%|█▍                              \n\n*** WARNING: max output size exceeded, skipping output. ***\n\n0 [16:17:39<7:30:07, 25.84s/it]\r 69%|███████████████████████▍          | 2316/3360 [16:18:06<7:32:21, 26.00s/it]\r 69%|███████████████████████▍          | 2317/3360 [16:18:31<7:27:38, 25.75s/it]\r 69%|███████████████████████▍          | 2318/3360 [16:18:58<7:33:09, 26.09s/it]\r 69%|███████████████████████▍          | 2319/3360 [16:19:20<7:14:09, 25.02s/it]\r 69%|███████████████████████▍          | 2320/3360 [16:19:42<6:58:38, 24.15s/it]\r                                                                                \r{'loss': 0.0554, 'grad_norm': 4.382505893707275, 'learning_rate': 2.645307173898901e-05, 'epoch': 4.14}\r\n\r 69%|███████████████████████▍          | 2320/3360 [16:19:42<6:58:38, 24.15s/it]\r 69%|███████████████████████▍          | 2321/3360 [16:20:10<7:14:58, 25.12s/it]\r 69%|███████████████████████▍          | 2322/3360 [16:20:38<7:30:35, 26.05s/it]\r 69%|███████████████████████▌          | 2323/3360 [16:21:04<7:31:33, 26.13s/it]\r 69%|███████████████████████▌          | 2324/3360 [16:21:29<7:25:01, 25.77s/it]\r 69%|███████████████████████▌          | 2325/3360 [16:21:56<7:28:06, 25.98s/it]\r 69%|███████████████████████▌          | 2326/3360 [16:22:18<7:10:49, 25.00s/it]\r 69%|███████████████████████▌          | 2327/3360 [16:22:44<7:11:57, 25.09s/it]\r 69%|███████████████���███████▌          | 2328/3360 [16:23:07<7:03:57, 24.65s/it]\r 69%|███████████████████████▌          | 2329/3360 [16:23:35<7:18:52, 25.54s/it]\r 69%|███████████████████████▌          | 2330/3360 [16:24:00<7:15:29, 25.37s/it]\r                                                                                \r{'loss': 0.0305, 'grad_norm': 2.086808919906616, 'learning_rate': 2.5996115501697694e-05, 'epoch': 4.16}\r\n\r 69%|███████████████████████▌          | 2330/3360 [16:24:00<7:15:29, 25.37s/it]\r 69%|███████████████████████▌          | 2331/3360 [16:24:21<6:53:09, 24.09s/it]\r 69%|███████████████████████▌          | 2332/3360 [16:24:46<6:56:34, 24.31s/it]\r 69%|███████████████████████▌          | 2333/3360 [16:25:14<7:14:19, 25.37s/it]\r 69%|███████████████████████▌          | 2334/3360 [16:25:36<6:59:33, 24.54s/it]\r 69%|███████████████████████▋          | 2335/3360 [16:26:03<7:10:36, 25.21s/it]\r 70%|███████████████████████▋          | 2336/3360 [16:26:29<7:12:47, 25.36s/it]\r 70%|███████████████████████▋          | 2337/3360 [16:26:56<7:22:57, 25.98s/it]\r 70%|███████████████████████▋          | 2338/3360 [16:27:18<7:02:34, 24.81s/it]\r 70%|███████████████████████▋          | 2339/3360 [16:27:43<7:01:15, 24.76s/it]\r 70%|███████████████████████▋          | 2340/3360 [16:28:06<6:54:00, 24.35s/it]\r                                                                                \r{'loss': 0.0597, 'grad_norm': 2.027472972869873, 'learning_rate': 2.5541749944535554e-05, 'epoch': 4.18}\r\n\r 70%|███████████████████████▋          | 2340/3360 [16:28:06<6:54:00, 24.35s/it]\r 70%|███████████████████████▋          | 2341/3360 [16:28:32<7:00:54, 24.78s/it]\r 70%|███████████████████████▋          | 2342/3360 [16:28:58<7:05:24, 25.07s/it]\r 70%|███████████████████████▋          | 2343/3360 [16:29:21<6:53:25, 24.39s/it]\r 70%|███████████████████████▋          | 2344/3360 [16:29:45<6:52:05, 24.34s/it]\r 70%|███████████████████████▋          | 2345/3360 [16:30:11<6:59:19, 24.79s/it]\r 70%|███████████████████████▋          | 2346/3360 [16:30:37<7:05:34, 25.18s/it]\r 70%|███████████████████████▋          | 2347/3360 [16:30:57<6:42:13, 23.82s/it]\r 70%|███████████████████████▊          | 2348/3360 [16:31:21<6:41:04, 23.78s/it]\r 70%|███████████████████████▊          | 2349/3360 [16:31:49<7:02:54, 25.10s/it]\r 70%|███████████████████████▊          | 2350/3360 [16:32:14<6:58:49, 24.88s/it]\r                                                                                \r{'loss': 0.043, 'grad_norm': 4.532371997833252, 'learning_rate': 2.5090024106057962e-05, 'epoch': 4.19}\r\n\r 70%|███████████████████████▊          | 2350/3360 [16:32:14<6:58:49, 24.88s/it]\r 70%|███████████████████████▊          | 2351/3360 [16:32:43<7:20:16, 26.18s/it]\r 70%|███████████████████████▊          | 2352/3360 [16:33:06<7:04:20, 25.26s/it]\r 70%|███████████████████████▊          | 2353/3360 [16:33:29<6:52:40, 24.59s/it]\r 70%|███████████████████████▊          | 2354/3360 [16:33:53<6:51:34, 24.55s/it]\r 70%|███████████████████████▊          | 2355/3360 [16:34:21<7:05:33, 25.41s/it]\r 70%|███████████████████████▊          | 2356/3360 [16:34:50<7:24:39, 26.57s/it]\r 70%|███████████████████████▊          | 2357/3360 [16:35:14<7:11:11, 25.79s/it]\r 70%|███████████████████████▊          | 2358/3360 [16:35:38<7:01:34, 25.24s/it]\r 70%|███████████████████████▊          | 2359/3360 [16:36:08<7:22:53, 26.55s/it]\r 70%|█████████████��█████████▉          | 2360/3360 [16:36:32<7:09:44, 25.78s/it]\r                                                                                \r{'loss': 0.05, 'grad_norm': 0.9692360758781433, 'learning_rate': 2.464098673992205e-05, 'epoch': 4.21}\r\n\r 70%|███████████████████████▉          | 2360/3360 [16:36:32<7:09:44, 25.78s/it]\r 70%|███████████████████████▉          | 2361/3360 [16:36:58<7:13:44, 26.05s/it]\r 70%|███████████████████████▉          | 2362/3360 [16:37:23<7:05:58, 25.61s/it]\r 70%|███████████████████████▉          | 2363/3360 [16:37:52<7:21:45, 26.59s/it]\r 70%|███████████████████████▉          | 2364/3360 [16:38:14<7:00:13, 25.32s/it]\r 70%|███████████████████████▉          | 2365/3360 [16:38:36<6:44:35, 24.40s/it]\r 70%|███████████████████████▉          | 2366/3360 [16:39:07<7:15:21, 26.28s/it]\r 70%|███████████████████████▉          | 2367/3360 [16:39:30<6:58:30, 25.29s/it]\r 70%|███████████████████████▉          | 2368/3360 [16:39:55<6:56:01, 25.16s/it]\r 71%|███████████████████████▉          | 2369/3360 [16:40:19<6:50:46, 24.87s/it]\r 71%|███████████████████████▉          | 2370/3360 [16:40:41<6:37:16, 24.08s/it]\r                                                                                \r{'loss': 0.0558, 'grad_norm': 2.5744211673736572, 'learning_rate': 2.4194686309624663e-05, 'epoch': 4.23}\r\n\r 71%|███████████████████████▉          | 2370/3360 [16:40:41<6:37:16, 24.08s/it]\r 71%|███████████████████████▉          | 2371/3360 [16:41:04<6:31:56, 23.78s/it]\r 71%|████████████████████████          | 2372/3360 [16:41:29<6:34:29, 23.96s/it]\r 71%|████████████████████████          | 2373/3360 [16:41:55<6:46:07, 24.69s/it]\r 71%|████████████████████████          | 2374/3360 [16:42:25<7:08:36, 26.08s/it]\r 71%|████████████████████████          | 2375/3360 [16:42:47<6:48:10, 24.86s/it]\r 71%|████████████████████████          | 2376/3360 [16:43:11<6:43:30, 24.60s/it]\r 71%|████████████████████████          | 2377/3360 [16:43:37<6:52:31, 25.18s/it]\r 71%|████████████████████████          | 2378/3360 [16:44:05<7:04:57, 25.96s/it]\r 71%|████████████████████████          | 2379/3360 [16:44:33<7:12:44, 26.47s/it]\r 71%|████████████████████████          | 2380/3360 [16:44:58<7:07:15, 26.16s/it]\r                                                                                \r{'loss': 0.0704, 'grad_norm': 3.8792245388031006, 'learning_rate': 2.3751170983272e-05, 'epoch': 4.25}\r\n\r 71%|████████████████████████          | 2380/3360 [16:44:58<7:07:15, 26.16s/it]\r 71%|████████████████████████          | 2381/3360 [16:45:26<7:18:28, 26.87s/it]\r 71%|████████████████████████          | 2382/3360 [16:45:50<6:59:34, 25.74s/it]\r 71%|████████████████████████          | 2383/3360 [16:46:10<6:34:56, 24.25s/it]\r 71%|████████████████████████          | 2384/3360 [16:46:33<6:24:50, 23.66s/it]\r 71%|████████████████████████▏         | 2385/3360 [16:46:58<6:32:06, 24.13s/it]\r 71%|████████████████████████▏         | 2386/3360 [16:47:25<6:48:21, 25.16s/it]\r 71%|████████████████████████▏         | 2387/3360 [16:47:54<7:06:02, 26.27s/it]\r 71%|████████████████████████▏         | 2388/3360 [16:48:17<6:50:01, 25.31s/it]\r 71%|████████████████████████▏         | 2389/3360 [16:48:40<6:36:39, 24.51s/it]\r 71%|████████████████████████▏         | 2390/3360 [16:49:04<6:32:48, 24.30s/it]\r                                                                                \r{'loss': 0.0381, 'grad_norm': 1.5790431499481201, 'learning_rate': 2.3310488628380757e-05, 'epoch': 4.27}\r\n\r 71%|████████████████████████▏         | 2390/3360 [16:49:04<6:32:48, 24.30s/it]\r 71%|████████████████████████▏         | 2391/3360 [16:49:26<6:22:33, 23.69s/it]\r 71%|████████████████████████▏         | 2392/3360 [16:49:49<6:19:25, 23.52s/it]\r 71%|████████████████████████▏         | 2393/3360 [16:50:11<6:12:40, 23.12s/it]\r 71%|████████████████████████▏         | 2394/3360 [16:50:33<6:05:23, 22.70s/it]\r 71%|████████████████████████▏         | 2395/3360 [16:51:00<6:23:17, 23.83s/it]\r 71%|████████████████████████▏         | 2396/3360 [16:51:27<6:42:32, 25.05s/it]\r 71%|████████████████████████▎         | 2397/3360 [16:51:50<6:31:27, 24.39s/it]\r 71%|████████████████████████▎         | 2398/3360 [16:52:20<6:56:03, 25.95s/it]\r 71%|████████████████████████▎         | 2399/3360 [16:52:48<7:05:35, 26.57s/it]\r 71%|████████████████████████▎         | 2400/3360 [16:53:12<6:51:07, 25.70s/it]\r                                                                                \r{'loss': 0.0442, 'grad_norm': 6.536630630493164, 'learning_rate': 2.2872686806712035e-05, 'epoch': 4.28}\r\n\r 71%|████████████████████████▎         | 2400/3360 [16:53:12<6:51:07, 25.70s/it]\r 71%|████████████████████████▎         | 2401/3360 [16:53:35<6:41:00, 25.09s/it]\r 71%|████████████████████████▎         | 2402/3360 [16:54:01<6:44:51, 25.36s/it]\r 72%|████████████████████████▎         | 2403/3360 [16:54:29<6:56:50, 26.13s/it]\r 72%|████████████████████████▎         | 2404/3360 [16:54:56<7:01:00, 26.42s/it]\r 72%|████████████████████████▎         | 2405/3360 [16:55:20<6:45:35, 25.48s/it]\r 72%|████████████████████████▎         | 2406/3360 [16:55:45<6:45:43, 25.52s/it]\r 72%|████████████████████████▎         | 2407/3360 [16:56:14<7:00:27, 26.47s/it]\r 72%|████████████████████████▎         | 2408/3360 [16:56:38<6:49:55, 25.84s/it]\r 72%|████████████████████████▍         | 2409/3360 [16:57:06<6:57:57, 26.37s/it]\r 72%|████████████████████████▍         | 2410/3360 [16:57:30<6:48:05, 25.77s/it]\r                                                                                \r{'loss': 0.0538, 'grad_norm': 2.2105183601379395, 'learning_rate': 2.243781276913811e-05, 'epoch': 4.3}\r\n\r 72%|████████████████████████▍         | 2410/3360 [16:57:30<6:48:05, 25.77s/it]\r 72%|████████████████████████▍         | 2411/3360 [16:57:52<6:28:58, 24.59s/it]\r 72%|████████████████████████▍         | 2412/3360 [16:58:16<6:25:27, 24.40s/it]\r 72%|████████████████████████▍         | 2413/3360 [16:58:40<6:20:56, 24.14s/it]\r 72%|████████████████████████▍         | 2414/3360 [16:59:03<6:18:17, 23.99s/it]\r 72%|████████████████████████▍         | 2415/3360 [16:59:25<6:05:41, 23.22s/it]\r 72%|████████████████████████▍         | 2416/3360 [16:59:48<6:08:15, 23.41s/it]\r 72%|████████████████████████▍         | 2417/3360 [17:00:16<6:26:42, 24.61s/it]\r 72%|████████████████████████▍         | 2418/3360 [17:00:43<6:39:51, 25.47s/it]\r 72%|████████████████████████▍         | 2419/3360 [17:01:09<6:38:19, 25.40s/it]\r 72%|████████████████████████▍         | 2420/3360 [17:01:34<6:38:42, 25.45s/it]\r                                                                                \r{'loss': 0.0306, 'grad_norm': 3.6631381511688232, 'learning_rate': 2.200591345054267e-05, 'epoch': 4.32}\r\n\r 72%|████████████████████████▍         | 2420/3360 [17:01:34<6:38:42, 25.45s/it]\r 72%|██████��█████████████████▍         | 2421/3360 [17:02:01<6:45:30, 25.91s/it]\r 72%|████████████████████████▌         | 2422/3360 [17:02:30<6:59:00, 26.80s/it]\r 72%|████████████████████████▌         | 2423/3360 [17:02:57<7:01:25, 26.99s/it]\r 72%|████████████████████████▌         | 2424/3360 [17:03:22<6:50:12, 26.30s/it]\r 72%|████████████████████████▌         | 2425/3360 [17:03:49<6:53:00, 26.50s/it]\r 72%|████████████████████████▌         | 2426/3360 [17:04:12<6:36:25, 25.47s/it]\r 72%|████████████████████████▌         | 2427/3360 [17:04:37<6:32:47, 25.26s/it]\r 72%|████████████████████████▌         | 2428/3360 [17:05:04<6:42:20, 25.90s/it]\r 72%|████████████████████████▌         | 2429/3360 [17:05:28<6:32:54, 25.32s/it]\r 72%|████████████████████████▌         | 2430/3360 [17:05:48<6:06:40, 23.66s/it]\r                                                                                \r{'loss': 0.0451, 'grad_norm': 2.3823962211608887, 'learning_rate': 2.157703546475539e-05, 'epoch': 4.34}\r\n\r 72%|████████████████████████▌         | 2430/3360 [17:05:48<6:06:40, 23.66s/it]\r 72%|████████████████████████▌         | 2431/3360 [17:06:18<6:35:36, 25.55s/it]\r 72%|████████████████████████▌         | 2432/3360 [17:06:44<6:39:01, 25.80s/it]\r 72%|████████████████████████▌         | 2433/3360 [17:07:04<6:11:10, 24.02s/it]\r 72%|████████████████████████▋         | 2434/3360 [17:07:26<6:01:35, 23.43s/it]\r 72%|████████████████████████▋         | 2435/3360 [17:07:50<6:00:04, 23.36s/it]\r 72%|████████████████████████▋         | 2436/3360 [17:08:16<6:15:18, 24.37s/it]\r 73%|████████████████████████▋         | 2437/3360 [17:08:41<6:14:28, 24.34s/it]\r 73%|████████████████████████▋         | 2438/3360 [17:09:08<6:28:57, 25.31s/it]\r 73%|████████████████████████▋         | 2439/3360 [17:09:34<6:28:59, 25.34s/it]\r 73%|████████████████████████▋         | 2440/3360 [17:09:59<6:27:40, 25.28s/it]\r                                                                                \r{'loss': 0.042, 'grad_norm': 5.382849216461182, 'learning_rate': 2.115122509952085e-05, 'epoch': 4.36}\r\n\r 73%|████████████████████████▋         | 2440/3360 [17:09:59<6:27:40, 25.28s/it]\r 73%|████████████████████████▋         | 2441/3360 [17:10:27<6:41:02, 26.18s/it]\r 73%|████████████████████████▋         | 2442/3360 [17:10:52<6:34:17, 25.77s/it]\r 73%|████████████████████████▋         | 2443/3360 [17:11:18<6:37:57, 26.04s/it]\r 73%|████████████████████████▋         | 2444/3360 [17:11:40<6:18:19, 24.78s/it]\r 73%|████████████████████████▋         | 2445/3360 [17:12:00<5:56:56, 23.41s/it]\r 73%|████████████████████████▊         | 2446/3360 [17:12:24<5:55:06, 23.31s/it]\r 73%|████████████████████████▊         | 2447/3360 [17:12:49<6:04:21, 23.94s/it]\r 73%|████████████████████████▊         | 2448/3360 [17:13:13<6:05:53, 24.07s/it]\r 73%|████████████████████████▊         | 2449/3360 [17:13:38<6:07:02, 24.17s/it]\r 73%|████████████████████████▊         | 2450/3360 [17:14:03<6:11:34, 24.50s/it]\r                                                                                \r{'loss': 0.0555, 'grad_norm': 3.1968250274658203, 'learning_rate': 2.0728528311502976e-05, 'epoch': 4.37}\r\n\r 73%|████████████████████████▊         | 2450/3360 [17:14:03<6:11:34, 24.50s/it]\r 73%|████████████████████████▊         | 2451/3360 [17:14:27<6:08:09, 24.30s/it]\r 73%|████████████████████████▊         | 2452/3360 [17:14:55<6:25:18, 25.46s/it]\r 73%|████████████████████████▊         | 2453/3360 [17:15:23<6:35:36, 26.17s/it]\r 73%|████████████████████████▊         | 2454/3360 [17:15:47<6:28:06, 25.70s/it]\r 73%|████████████████████████▊         | 2455/3360 [17:16:18<6:47:40, 27.03s/it]\r 73%|████████████████████████▊         | 2456/3360 [17:16:44<6:45:34, 26.92s/it]\r 73%|████████████████████████▊         | 2457/3360 [17:17:07<6:26:03, 25.65s/it]\r 73%|████████████████████████▊         | 2458/3360 [17:17:34<6:33:21, 26.17s/it]\r 73%|████████████████████████▉         | 2459/3360 [17:17:58<6:21:14, 25.39s/it]\r 73%|████████████████████████▉         | 2460/3360 [17:18:21<6:10:37, 24.71s/it]\r                                                                                \r{'loss': 0.0479, 'grad_norm': 3.747589349746704, 'learning_rate': 2.0308990721324927e-05, 'epoch': 4.39}\r\n\r 73%|████████████████████████▉         | 2460/3360 [17:18:21<6:10:37, 24.71s/it]\r 73%|████████████████████████▉         | 2461/3360 [17:18:48<6:19:54, 25.36s/it]\r 73%|████████████████████████▉         | 2462/3360 [17:19:12<6:14:20, 25.01s/it]\r 73%|████████████████████████▉         | 2463/3360 [17:19:36<6:07:57, 24.61s/it]\r 73%|████████████████████████▉         | 2464/3360 [17:20:00<6:04:52, 24.43s/it]\r 73%|████████████████████████▉         | 2465/3360 [17:20:24<6:03:03, 24.34s/it]\r 73%|████████████████████████▉         | 2466/3360 [17:20:49<6:05:00, 24.50s/it]\r 73%|████████████████████████▉         | 2467/3360 [17:21:14<6:08:02, 24.73s/it]\r 73%|████████████████████████▉         | 2468/3360 [17:21:39<6:09:40, 24.87s/it]\r 73%|████████████████████████▉         | 2469/3360 [17:22:04<6:06:46, 24.70s/it]\r 74%|████████████████████████▉         | 2470/3360 [17:22:25<5:53:50, 23.86s/it]\r                                                                                \r{'loss': 0.0407, 'grad_norm': 1.606154441833496, 'learning_rate': 1.989265760864542e-05, 'epoch': 4.41}\r\n\r 74%|████████████████████████▉         | 2470/3360 [17:22:25<5:53:50, 23.86s/it]\r 74%|█████████████████████████         | 2471/3360 [17:22:54<6:16:14, 25.39s/it]\r 74%|█████████████████████████         | 2472/3360 [17:23:20<6:14:52, 25.33s/it]\r 74%|█████████████████████████         | 2473/3360 [17:23:47<6:23:19, 25.93s/it]\r 74%|█████████████████████████         | 2474/3360 [17:24:11<6:16:07, 25.47s/it]\r 74%|█████████████████████████         | 2475/3360 [17:24:39<6:26:53, 26.23s/it]\r 74%|█████████████████████████         | 2476/3360 [17:25:07<6:33:52, 26.73s/it]\r 74%|█████████████████████████         | 2477/3360 [17:25:29<6:11:38, 25.25s/it]\r 74%|█████████████████████████         | 2478/3360 [17:25:54<6:09:16, 25.12s/it]\r 74%|█████████████████████████         | 2479/3360 [17:26:21<6:18:11, 25.76s/it]\r 74%|█████████████████████████         | 2480/3360 [17:26:45<6:09:59, 25.23s/it]\r                                                                                \r{'loss': 0.0464, 'grad_norm': 1.0993458032608032, 'learning_rate': 1.947957390727185e-05, 'epoch': 4.43}\r\n\r 74%|█████████████████████████         | 2480/3360 [17:26:45<6:09:59, 25.23s/it]\r 74%|█████████████████████████         | 2481/3360 [17:27:10<6:10:03, 25.26s/it]\r 74%|█████████████████████████         | 2482/3360 [17:27:35<6:07:47, 25.13s/it]\r 74%|█████████████████████████▏        | 2483/3360 [17:28:03<6:18:26, 25.89s/it]\r 74%|█████████████████████████▏        | 2484/3360 [17:28:30<6:22:55, 26.23s/it]\r 74%|█████████████████████████▏        | 2485/3360 [17:28:56<6:19:45, 26.04s/it]\r 74%|█████████████████████████▏        | 2486/3360 [17:29:17<5:57:30, 24.54s/it]\r 74%|█████████████████████████▏        | 2487/3360 [17:29:42<5:59:54, 24.74s/it]\r 74%|█████████████████████████▏        | 2488/3360 [17:30:03<5:43:01, 23.60s/it]\r 74%|█████████████████████████▏        | 2489/3360 [17:30:32<6:07:09, 25.29s/it]\r 74%|█████████████████████████▏        | 2490/3360 [17:30:59<6:13:52, 25.78s/it]\r                                                                                \r{'loss': 0.0325, 'grad_norm': 2.387045383453369, 'learning_rate': 1.906978420031059e-05, 'epoch': 4.44}\r\n\r 74%|█████████████████████████▏        | 2490/3360 [17:30:59<6:13:52, 25.78s/it]\r 74%|█████████████████████████▏        | 2491/3360 [17:31:24<6:09:06, 25.49s/it]\r 74%|█████████████████████████▏        | 2492/3360 [17:31:48<6:02:26, 25.05s/it]\r 74%|█████████████████████████▏        | 2493/3360 [17:32:14<6:05:25, 25.29s/it]\r 74%|█████████████████████████▏        | 2494/3360 [17:32:35<5:50:11, 24.26s/it]\r 74%|█████████████████████████▏        | 2495/3360 [17:32:59<5:48:18, 24.16s/it]\r 74%|█████████████████████████▎        | 2496/3360 [17:33:23<5:44:57, 23.96s/it]\r 74%|█████████████████████████▎        | 2497/3360 [17:33:47<5:44:57, 23.98s/it]\r 74%|█████████████████████████▎        | 2498/3360 [17:34:07<5:26:15, 22.71s/it]\r 74%|█████████████████████████▎        | 2499/3360 [17:34:32<5:36:30, 23.45s/it]\r 74%|█████████████████████████▎        | 2500/3360 [17:34:55<5:34:20, 23.33s/it]\r                                                                                \r{'loss': 0.0285, 'grad_norm': 0.8392044901847839, 'learning_rate': 1.8663332715355396e-05, 'epoch': 4.46}\r\n\r 74%|█████████████████████████▎        | 2500/3360 [17:34:55<5:34:20, 23.33s/it]\r 74%|█████████████████████████▎        | 2501/3360 [17:35:19<5:36:42, 23.52s/it]\r 74%|█████████████████████████▎        | 2502/3360 [17:35:44<5:44:47, 24.11s/it]\r 74%|█████████████████████████▎        | 2503/3360 [17:36:07<5:40:15, 23.82s/it]\r 75%|█████████████████████████▎        | 2504/3360 [17:36:35<5:55:15, 24.90s/it]\r 75%|█████████████████████████▎        | 2505/3360 [17:37:01<5:59:08, 25.20s/it]\r 75%|█████████████████████████▎        | 2506/3360 [17:37:26<5:57:42, 25.13s/it]\r 75%|█████████████████████████▎        | 2507/3360 [17:37:51<5:57:54, 25.18s/it]\r 75%|█████████████████████████▍        | 2508/3360 [17:38:16<5:57:15, 25.16s/it]\r 75%|█████████████████████████▍        | 2509/3360 [17:38:42<5:58:15, 25.26s/it]\r 75%|█████████████████████████▍        | 2510/3360 [17:39:05<5:48:04, 24.57s/it]\r                                                                                \r{'loss': 0.048, 'grad_norm': 8.342588424682617, 'learning_rate': 1.8260263319713844e-05, 'epoch': 4.48}\r\n\r 75%|█████████████████████████▍        | 2510/3360 [17:39:05<5:48:04, 24.57s/it]\r 75%|█████████████████████████▍        | 2511/3360 [17:39:26<5:33:22, 23.56s/it]\r 75%|█████████████████████████▍        | 2512/3360 [17:39:48<5:28:09, 23.22s/it]\r 75%|█████████████████████████▍        | 2513/3360 [17:40:18<5:55:57, 25.22s/it]\r 75%|█████████████████████████▍        | 2514/3360 [17:40:43<5:54:38, 25.15s/it]\r 75%|█████████████████████████▍        | 2515/3360 [17:41:05<5:40:08, 24.15s/it]\r 75%|█████████████████████████▍        | 2516/3360 [17:41:32<5:51:04, 24.96s/it]\r 75%|█████████████████████████▍        | 2517/3360 [17:41:55<5:43:44, 24.47s/it]\r 75%|█████████████████████████▍        | 2518/3360 [17:42:20<5:43:29, 24.48s/it]\r 75%|█████████████████████████▍        | 2519/3360 [17:42:44<5:44:44, 24.60s/it]\r 75%|█████████████████████████▌        | 2520/3360 [17:43:13<6:00:52, 25.78s/it]\r                                                                                \r{'loss': 0.033, 'grad_norm': 3.559077739715576, 'learning_rate': 1.7860619515673033e-05, 'epoch': 4.5}\r\n\r 75%|█████████████████████████▌        | 2520/3360 [17:43:13<6:00:52, 25.78s/it]\r 75%|█████████████████████████▌        | 2521/3360 [17:43:37<5:54:44, 25.37s/it]\r 75%|█████████████████████████▌        | 2522/3360 [17:44:02<5:49:13, 25.00s/it]\r 75%|█████████████████████████▌        | 2523/3360 [17:44:30<6:05:27, 26.20s/it]\r 75%|█████████████████████████▌        | 2524/3360 [17:44:54<5:55:14, 25.50s/it]\r 75%|█████████████████████████▌        | 2525/3360 [17:45:19<5:52:00, 25.29s/it]\r 75%|█████████████████████████▌        | 2526/3360 [17:45:44<5:48:18, 25.06s/it]\r 75%|█████████████████████████▌        | 2527/3360 [17:46:10<5:54:01, 25.50s/it]\r 75%|█████████████████████████▌        | 2528/3360 [17:46:35<5:50:43, 25.29s/it]\r 75%|█████████████████████████▌        | 2529/3360 [17:47:02<5:58:26, 25.88s/it]\r 75%|█████████████████████████▌        | 2530/3360 [17:47:27<5:54:04, 25.60s/it]\r                                                                                \r{'loss': 0.0372, 'grad_norm': 1.5533121824264526, 'learning_rate': 1.746444443580433e-05, 'epoch': 4.52}\r\n\r 75%|█████████████████████████▌        | 2530/3360 [17:47:27<5:54:04, 25.60s/it]\r 75%|█████████████████████████▌        | 2531/3360 [17:47:54<5:56:42, 25.82s/it]\r 75%|█████████████████████████▌        | 2532/3360 [17:48:19<5:56:21, 25.82s/it]\r 75%|█████████████████████████▋        | 2533/3360 [17:48:43<5:48:05, 25.25s/it]\r 75%|█████████████████████████▋        | 2534/3360 [17:49:10<5:54:05, 25.72s/it]\r 75%|█████████████████████████▋        | 2535/3360 [17:49:40<6:09:16, 26.86s/it]\r 75%|█████████████████████████▋        | 2536/3360 [17:50:05<6:02:42, 26.41s/it]\r 76%|█████████████████████████▋        | 2537/3360 [17:50:33<6:08:18, 26.85s/it]\r 76%|█████████████████████████▋        | 2538/3360 [17:50:57<5:55:47, 25.97s/it]\r 76%|█████████████████████████▋        | 2539/3360 [17:51:20<5:43:15, 25.09s/it]\r 76%|█████████████████████████▋        | 2540/3360 [17:51:48<5:55:36, 26.02s/it]\r                                                                                \r{'loss': 0.0621, 'grad_norm': 4.418670177459717, 'learning_rate': 1.7071780838308288e-05, 'epoch': 4.53}\r\n\r 76%|█████████████████████████▋        | 2540/3360 [17:51:48<5:55:36, 26.02s/it]\r 76%|█████████████████████████▋        | 2541/3360 [17:52:14<5:54:53, 26.00s/it]\r 76%|█████████████████████████▋        | 2542/3360 [17:52:40<5:53:16, 25.91s/it]\r 76%|█████████████████████████▋        | 2543/3360 [17:53:02<5:39:36, 24.94s/it]\r 76%|█████████████████████████▋        | 2544/3360 [17:53:29<5:48:07, 25.60s/it]\r 76%|█████████████████████████▊        | 2545/3360 [17:53:57<5:57:16, 26.30s/it]\r 76%|█████████████████████████▊        | 2546/3360 [17:54:21<5:47:04, 25.58s/it]\r 76%|█████████████████████████▊        | 2547/3360 [17:54:50<5:57:17, 26.37s/it]"
      ]
     }
    ],
@@ -390,42 +390,288 @@
     }
    },
    "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/Workspace/Users/donghao.huang@mastercard.com/llm-finetuning\r\n"
-     ]
-    },
     {
      "output_type": "display_data",
      "data": {
-      "text/html": [
-       "<style scoped>\n",
-       "  .ansiout {\n",
-       "    display: block;\n",
-       "    unicode-bidi: embed;\n",
-       "    white-space: pre-wrap;\n",
-       "    word-wrap: break-word;\n",
-       "    word-break: break-all;\n",
-       "    font-family: \"Menlo\", \"Monaco\", \"Consolas\", \"Ubuntu Mono\", \"Source Code Pro\", monospace;\n",
-       "    font-size: 13px;\n",
-       "    color: #555;\n",
-       "    margin-left: 4px;\n",
-       "    line-height: 19px;\n",
-       "  }\n",
-       "</style>"
+      "text/plain": [
+       "com.databricks.backend.common.rpc.CommandCancelledException\n",
+       "\tat com.databricks.spark.chauffeur.ExecContextState.cancel(ExecContextState.scala:429)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.cancelExecution(ChauffeurState.scala:1225)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.$anonfun$process$1(ChauffeurState.scala:958)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)\n",
+       "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionContext(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionTags(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperationWithResultTags(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperation(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.process(ChauffeurState.scala:914)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequest$1(Chauffeur.scala:679)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.$anonfun$applyOrElse$5(Chauffeur.scala:705)\n",
+       "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)\n",
+       "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequestWithUsageLogging$1(Chauffeur.scala:704)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:759)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:552)\n",
+       "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive0$2(ServerBackend.scala:174)\n",
+       "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)\n",
+       "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)\n",
+       "\tat com.databricks.rpc.ServerBackend.internalReceive0(ServerBackend.scala:171)\n",
+       "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive$1(ServerBackend.scala:147)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)\n",
+       "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)\n",
+       "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)\n",
+       "\tat com.databricks.rpc.ServerBackend.recordOperation(ServerBackend.scala:22)\n",
+       "\tat com.databricks.rpc.ServerBackend.internalReceive(ServerBackend.scala:146)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.handleRPC(JettyServer.scala:1021)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.handleRequestAndRespond(JettyServer.scala:942)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6(JettyServer.scala:546)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6$adapted(JettyServer.scala:515)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$6(ActivityContextFactory.scala:546)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.withAttributionContext(ActivityContextFactory.scala:57)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$3(ActivityContextFactory.scala:546)\n",
+       "\tat com.databricks.context.integrity.IntegrityCheckContext$ThreadLocalStorage$.withValue(IntegrityCheckContext.scala:72)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.withActivityInternal(ActivityContextFactory.scala:524)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.withServiceRequestActivity(ActivityContextFactory.scala:178)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.handleHttp(JettyServer.scala:515)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.doPost(JettyServer.scala:405)\n",
+       "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:665)\n",
+       "\tat com.databricks.rpc.HttpServletWithPatch.service(HttpServletWithPatch.scala:33)\n",
+       "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:750)\n",
+       "\tat org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:799)\n",
+       "\tat org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:554)\n",
+       "\tat org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:190)\n",
+       "\tat org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:505)\n",
+       "\tat org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)\n",
+       "\tat org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:127)\n",
+       "\tat org.eclipse.jetty.server.Server.handle(Server.java:516)\n",
+       "\tat org.eclipse.jetty.server.HttpChannel.lambda$handle$1(HttpChannel.java:487)\n",
+       "\tat org.eclipse.jetty.server.HttpChannel.dispatch(HttpChannel.java:732)\n",
+       "\tat org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:479)\n",
+       "\tat org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:277)\n",
+       "\tat org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:311)\n",
+       "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)\n",
+       "\tat org.eclipse.jetty.io.ssl.SslConnection$DecryptedEndPoint.onFillable(SslConnection.java:555)\n",
+       "\tat org.eclipse.jetty.io.ssl.SslConnection.onFillable(SslConnection.java:410)\n",
+       "\tat org.eclipse.jetty.io.ssl.SslConnection$2.succeeded(SslConnection.java:164)\n",
+       "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)\n",
+       "\tat org.eclipse.jetty.io.ChannelEndPoint$1.run(ChannelEndPoint.java:104)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.runTask(EatWhatYouKill.java:338)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:315)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.run(EatWhatYouKill.java:131)\n",
+       "\tat org.eclipse.jetty.util.thread.ReservedThreadExecutor$ReservedThread.run(ReservedThreadExecutor.java:409)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$2(InstrumentedQueuedThreadPool.scala:106)\n",
+       "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.withAttributionContext(InstrumentedQueuedThreadPool.scala:46)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$1(InstrumentedQueuedThreadPool.scala:106)\n",
+       "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)\n",
+       "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads(QueuedThreadPoolInstrumenter.scala:150)\n",
+       "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads$(QueuedThreadPoolInstrumenter.scala:147)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.trackActiveThreads(InstrumentedQueuedThreadPool.scala:46)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.run(InstrumentedQueuedThreadPool.scala:88)\n",
+       "\tat org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883)\n",
+       "\tat org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034)\n",
+       "\tat java.lang.Thread.run(Thread.java:750)"
       ]
      },
      "metadata": {
       "application/vnd.databricks.v1+output": {
+       "addedWidgets": {},
        "arguments": {},
-       "data": "",
-       "errorSummary": "",
-       "errorTraceType": null,
-       "metadata": {},
-       "type": "ipynbError"
+       "datasetInfos": [],
+       "jupyterProps": null,
+       "metadata": {
+        "errorSummary": "Cancelled"
+       },
+       "removedWidgets": [],
+       "sqlProps": null,
+       "stackFrames": [
+        "com.databricks.backend.common.rpc.CommandCancelledException",
+        "\tat com.databricks.spark.chauffeur.ExecContextState.cancel(ExecContextState.scala:429)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.cancelExecution(ChauffeurState.scala:1225)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.$anonfun$process$1(ChauffeurState.scala:958)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)",
+        "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionContext(ChauffeurState.scala:67)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionTags(ChauffeurState.scala:67)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperationWithResultTags(ChauffeurState.scala:67)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperation(ChauffeurState.scala:67)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.process(ChauffeurState.scala:914)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequest$1(Chauffeur.scala:679)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.$anonfun$applyOrElse$5(Chauffeur.scala:705)",
+        "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)",
+        "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequestWithUsageLogging$1(Chauffeur.scala:704)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:759)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:552)",
+        "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive0$2(ServerBackend.scala:174)",
+        "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)",
+        "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)",
+        "\tat com.databricks.rpc.ServerBackend.internalReceive0(ServerBackend.scala:171)",
+        "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive$1(ServerBackend.scala:147)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)",
+        "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)",
+        "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)",
+        "\tat com.databricks.rpc.ServerBackend.recordOperation(ServerBackend.scala:22)",
+        "\tat com.databricks.rpc.ServerBackend.internalReceive(ServerBackend.scala:146)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.handleRPC(JettyServer.scala:1021)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.handleRequestAndRespond(JettyServer.scala:942)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6(JettyServer.scala:546)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6$adapted(JettyServer.scala:515)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$6(ActivityContextFactory.scala:546)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.withAttributionContext(ActivityContextFactory.scala:57)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$3(ActivityContextFactory.scala:546)",
+        "\tat com.databricks.context.integrity.IntegrityCheckContext$ThreadLocalStorage$.withValue(IntegrityCheckContext.scala:72)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.withActivityInternal(ActivityContextFactory.scala:524)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.withServiceRequestActivity(ActivityContextFactory.scala:178)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.handleHttp(JettyServer.scala:515)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.doPost(JettyServer.scala:405)",
+        "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:665)",
+        "\tat com.databricks.rpc.HttpServletWithPatch.service(HttpServletWithPatch.scala:33)",
+        "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:750)",
+        "\tat org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:799)",
+        "\tat org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:554)",
+        "\tat org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:190)",
+        "\tat org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:505)",
+        "\tat org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)",
+        "\tat org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:127)",
+        "\tat org.eclipse.jetty.server.Server.handle(Server.java:516)",
+        "\tat org.eclipse.jetty.server.HttpChannel.lambda$handle$1(HttpChannel.java:487)",
+        "\tat org.eclipse.jetty.server.HttpChannel.dispatch(HttpChannel.java:732)",
+        "\tat org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:479)",
+        "\tat org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:277)",
+        "\tat org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:311)",
+        "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)",
+        "\tat org.eclipse.jetty.io.ssl.SslConnection$DecryptedEndPoint.onFillable(SslConnection.java:555)",
+        "\tat org.eclipse.jetty.io.ssl.SslConnection.onFillable(SslConnection.java:410)",
+        "\tat org.eclipse.jetty.io.ssl.SslConnection$2.succeeded(SslConnection.java:164)",
+        "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)",
+        "\tat org.eclipse.jetty.io.ChannelEndPoint$1.run(ChannelEndPoint.java:104)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.runTask(EatWhatYouKill.java:338)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:315)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.run(EatWhatYouKill.java:131)",
+        "\tat org.eclipse.jetty.util.thread.ReservedThreadExecutor$ReservedThread.run(ReservedThreadExecutor.java:409)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$2(InstrumentedQueuedThreadPool.scala:106)",
+        "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.withAttributionContext(InstrumentedQueuedThreadPool.scala:46)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$1(InstrumentedQueuedThreadPool.scala:106)",
+        "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)",
+        "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads(QueuedThreadPoolInstrumenter.scala:150)",
+        "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads$(QueuedThreadPoolInstrumenter.scala:147)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.trackActiveThreads(InstrumentedQueuedThreadPool.scala:46)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.run(InstrumentedQueuedThreadPool.scala:88)",
+        "\tat org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883)",
+        "\tat org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034)",
+        "\tat java.lang.Thread.run(Thread.java:750)"
+       ],
+       "type": "baseError"
       }
      },
      "output_type": "display_data"
@@ -464,31 +710,285 @@
     {
      "output_type": "display_data",
      "data": {
-      "text/html": [
-       "<style scoped>\n",
-       "  .ansiout {\n",
-       "    display: block;\n",
-       "    unicode-bidi: embed;\n",
-       "    white-space: pre-wrap;\n",
-       "    word-wrap: break-word;\n",
-       "    word-break: break-all;\n",
-       "    font-family: \"Menlo\", \"Monaco\", \"Consolas\", \"Ubuntu Mono\", \"Source Code Pro\", monospace;\n",
-       "    font-size: 13px;\n",
-       "    color: #555;\n",
-       "    margin-left: 4px;\n",
-       "    line-height: 19px;\n",
-       "  }\n",
-       "</style>"
+      "text/plain": [
+       "com.databricks.backend.common.rpc.CommandCancelledException\n",
+       "\tat com.databricks.spark.chauffeur.ExecContextState.cancel(ExecContextState.scala:429)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.cancelExecution(ChauffeurState.scala:1225)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.$anonfun$process$1(ChauffeurState.scala:958)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)\n",
+       "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionContext(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionTags(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperationWithResultTags(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperation(ChauffeurState.scala:67)\n",
+       "\tat com.databricks.spark.chauffeur.ChauffeurState.process(ChauffeurState.scala:914)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequest$1(Chauffeur.scala:679)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.$anonfun$applyOrElse$5(Chauffeur.scala:705)\n",
+       "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)\n",
+       "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequestWithUsageLogging$1(Chauffeur.scala:704)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:759)\n",
+       "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:552)\n",
+       "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive0$2(ServerBackend.scala:174)\n",
+       "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)\n",
+       "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)\n",
+       "\tat com.databricks.rpc.ServerBackend.internalReceive0(ServerBackend.scala:171)\n",
+       "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive$1(ServerBackend.scala:147)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)\n",
+       "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)\n",
+       "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)\n",
+       "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)\n",
+       "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)\n",
+       "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)\n",
+       "\tat com.databricks.rpc.ServerBackend.recordOperation(ServerBackend.scala:22)\n",
+       "\tat com.databricks.rpc.ServerBackend.internalReceive(ServerBackend.scala:146)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.handleRPC(JettyServer.scala:1021)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.handleRequestAndRespond(JettyServer.scala:942)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6(JettyServer.scala:546)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6$adapted(JettyServer.scala:515)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$6(ActivityContextFactory.scala:546)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.withAttributionContext(ActivityContextFactory.scala:57)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$3(ActivityContextFactory.scala:546)\n",
+       "\tat com.databricks.context.integrity.IntegrityCheckContext$ThreadLocalStorage$.withValue(IntegrityCheckContext.scala:72)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.withActivityInternal(ActivityContextFactory.scala:524)\n",
+       "\tat com.databricks.logging.activity.ActivityContextFactory$.withServiceRequestActivity(ActivityContextFactory.scala:178)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.handleHttp(JettyServer.scala:515)\n",
+       "\tat com.databricks.rpc.JettyServer$RequestManager.doPost(JettyServer.scala:405)\n",
+       "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:665)\n",
+       "\tat com.databricks.rpc.HttpServletWithPatch.service(HttpServletWithPatch.scala:33)\n",
+       "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:750)\n",
+       "\tat org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:799)\n",
+       "\tat org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:554)\n",
+       "\tat org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:190)\n",
+       "\tat org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:505)\n",
+       "\tat org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)\n",
+       "\tat org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:127)\n",
+       "\tat org.eclipse.jetty.server.Server.handle(Server.java:516)\n",
+       "\tat org.eclipse.jetty.server.HttpChannel.lambda$handle$1(HttpChannel.java:487)\n",
+       "\tat org.eclipse.jetty.server.HttpChannel.dispatch(HttpChannel.java:732)\n",
+       "\tat org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:479)\n",
+       "\tat org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:277)\n",
+       "\tat org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:311)\n",
+       "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)\n",
+       "\tat org.eclipse.jetty.io.ssl.SslConnection$DecryptedEndPoint.onFillable(SslConnection.java:555)\n",
+       "\tat org.eclipse.jetty.io.ssl.SslConnection.onFillable(SslConnection.java:410)\n",
+       "\tat org.eclipse.jetty.io.ssl.SslConnection$2.succeeded(SslConnection.java:164)\n",
+       "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)\n",
+       "\tat org.eclipse.jetty.io.ChannelEndPoint$1.run(ChannelEndPoint.java:104)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.runTask(EatWhatYouKill.java:338)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:315)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173)\n",
+       "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.run(EatWhatYouKill.java:131)\n",
+       "\tat org.eclipse.jetty.util.thread.ReservedThreadExecutor$ReservedThread.run(ReservedThreadExecutor.java:409)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$2(InstrumentedQueuedThreadPool.scala:106)\n",
+       "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)\n",
+       "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)\n",
+       "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)\n",
+       "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)\n",
+       "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.withAttributionContext(InstrumentedQueuedThreadPool.scala:46)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$1(InstrumentedQueuedThreadPool.scala:106)\n",
+       "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)\n",
+       "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads(QueuedThreadPoolInstrumenter.scala:150)\n",
+       "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads$(QueuedThreadPoolInstrumenter.scala:147)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.trackActiveThreads(InstrumentedQueuedThreadPool.scala:46)\n",
+       "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.run(InstrumentedQueuedThreadPool.scala:88)\n",
+       "\tat org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883)\n",
+       "\tat org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034)\n",
+       "\tat java.lang.Thread.run(Thread.java:750)"
       ]
      },
      "metadata": {
       "application/vnd.databricks.v1+output": {
+       "addedWidgets": {},
        "arguments": {},
-       "data": "",
-       "errorSummary": "",
-       "errorTraceType": null,
-       "metadata": {},
-       "type": "ipynbError"
+       "datasetInfos": [],
+       "jupyterProps": null,
+       "metadata": {
+        "errorSummary": "Cancelled"
+       },
+       "removedWidgets": [],
+       "sqlProps": null,
+       "stackFrames": [
+        "com.databricks.backend.common.rpc.CommandCancelledException",
+        "\tat com.databricks.spark.chauffeur.ExecContextState.cancel(ExecContextState.scala:429)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.cancelExecution(ChauffeurState.scala:1225)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.$anonfun$process$1(ChauffeurState.scala:958)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)",
+        "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionContext(ChauffeurState.scala:67)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.withAttributionTags(ChauffeurState.scala:67)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperationWithResultTags(ChauffeurState.scala:67)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.recordOperation(ChauffeurState.scala:67)",
+        "\tat com.databricks.spark.chauffeur.ChauffeurState.process(ChauffeurState.scala:914)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequest$1(Chauffeur.scala:679)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.$anonfun$applyOrElse$5(Chauffeur.scala:705)",
+        "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)",
+        "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.handleDriverRequestWithUsageLogging$1(Chauffeur.scala:704)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:759)",
+        "\tat com.databricks.spark.chauffeur.Chauffeur$$anon$1$$anonfun$receive$1.applyOrElse(Chauffeur.scala:552)",
+        "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive0$2(ServerBackend.scala:174)",
+        "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)",
+        "\tat com.databricks.rpc.ServerBackend$$anonfun$commonReceive$1.applyOrElse(ServerBackend.scala:200)",
+        "\tat com.databricks.rpc.ServerBackend.internalReceive0(ServerBackend.scala:171)",
+        "\tat com.databricks.rpc.ServerBackend.$anonfun$internalReceive$1(ServerBackend.scala:147)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperation$1(UsageLogging.scala:525)",
+        "\tat com.databricks.logging.UsageLogging.executeThunkAndCaptureResultTags$1(UsageLogging.scala:629)",
+        "\tat com.databricks.logging.UsageLogging.$anonfun$recordOperationWithResultTags$4(UsageLogging.scala:647)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionContext(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags(AttributionContextTracing.scala:95)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionTags$(AttributionContextTracing.scala:76)",
+        "\tat com.databricks.rpc.ServerBackend.withAttributionTags(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags(UsageLogging.scala:624)",
+        "\tat com.databricks.logging.UsageLogging.recordOperationWithResultTags$(UsageLogging.scala:534)",
+        "\tat com.databricks.rpc.ServerBackend.recordOperationWithResultTags(ServerBackend.scala:22)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation(UsageLogging.scala:526)",
+        "\tat com.databricks.logging.UsageLogging.recordOperation$(UsageLogging.scala:494)",
+        "\tat com.databricks.rpc.ServerBackend.recordOperation(ServerBackend.scala:22)",
+        "\tat com.databricks.rpc.ServerBackend.internalReceive(ServerBackend.scala:146)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.handleRPC(JettyServer.scala:1021)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.handleRequestAndRespond(JettyServer.scala:942)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6(JettyServer.scala:546)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.$anonfun$handleHttp$6$adapted(JettyServer.scala:515)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$6(ActivityContextFactory.scala:546)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.withAttributionContext(ActivityContextFactory.scala:57)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.$anonfun$withActivityInternal$3(ActivityContextFactory.scala:546)",
+        "\tat com.databricks.context.integrity.IntegrityCheckContext$ThreadLocalStorage$.withValue(IntegrityCheckContext.scala:72)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.withActivityInternal(ActivityContextFactory.scala:524)",
+        "\tat com.databricks.logging.activity.ActivityContextFactory$.withServiceRequestActivity(ActivityContextFactory.scala:178)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.handleHttp(JettyServer.scala:515)",
+        "\tat com.databricks.rpc.JettyServer$RequestManager.doPost(JettyServer.scala:405)",
+        "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:665)",
+        "\tat com.databricks.rpc.HttpServletWithPatch.service(HttpServletWithPatch.scala:33)",
+        "\tat javax.servlet.http.HttpServlet.service(HttpServlet.java:750)",
+        "\tat org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:799)",
+        "\tat org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:554)",
+        "\tat org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:190)",
+        "\tat org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:505)",
+        "\tat org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)",
+        "\tat org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:127)",
+        "\tat org.eclipse.jetty.server.Server.handle(Server.java:516)",
+        "\tat org.eclipse.jetty.server.HttpChannel.lambda$handle$1(HttpChannel.java:487)",
+        "\tat org.eclipse.jetty.server.HttpChannel.dispatch(HttpChannel.java:732)",
+        "\tat org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:479)",
+        "\tat org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:277)",
+        "\tat org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:311)",
+        "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)",
+        "\tat org.eclipse.jetty.io.ssl.SslConnection$DecryptedEndPoint.onFillable(SslConnection.java:555)",
+        "\tat org.eclipse.jetty.io.ssl.SslConnection.onFillable(SslConnection.java:410)",
+        "\tat org.eclipse.jetty.io.ssl.SslConnection$2.succeeded(SslConnection.java:164)",
+        "\tat org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:105)",
+        "\tat org.eclipse.jetty.io.ChannelEndPoint$1.run(ChannelEndPoint.java:104)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.runTask(EatWhatYouKill.java:338)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:315)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173)",
+        "\tat org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.run(EatWhatYouKill.java:131)",
+        "\tat org.eclipse.jetty.util.thread.ReservedThreadExecutor$ReservedThread.run(ReservedThreadExecutor.java:409)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$2(InstrumentedQueuedThreadPool.scala:106)",
+        "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)",
+        "\tat com.databricks.logging.AttributionContextTracing.$anonfun$withAttributionContext$1(AttributionContextTracing.scala:48)",
+        "\tat com.databricks.logging.AttributionContext$.$anonfun$withValue$1(AttributionContext.scala:244)",
+        "\tat scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)",
+        "\tat com.databricks.logging.AttributionContext$.withValue(AttributionContext.scala:240)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext(AttributionContextTracing.scala:46)",
+        "\tat com.databricks.logging.AttributionContextTracing.withAttributionContext$(AttributionContextTracing.scala:43)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.withAttributionContext(InstrumentedQueuedThreadPool.scala:46)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.$anonfun$run$1(InstrumentedQueuedThreadPool.scala:106)",
+        "\tat scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)",
+        "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads(QueuedThreadPoolInstrumenter.scala:150)",
+        "\tat com.databricks.instrumentation.QueuedThreadPoolInstrumenter.trackActiveThreads$(QueuedThreadPoolInstrumenter.scala:147)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool.trackActiveThreads(InstrumentedQueuedThreadPool.scala:46)",
+        "\tat com.databricks.rpc.InstrumentedQueuedThreadPool$$anon$1.run(InstrumentedQueuedThreadPool.scala:88)",
+        "\tat org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883)",
+        "\tat org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034)",
+        "\tat java.lang.Thread.run(Thread.java:750)"
+       ],
+       "type": "baseError"
       }
      },
      "output_type": "display_data"