Hugging Face's logo

Femboyuwu2000
/
working

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Femboyuwu2000 commited on
Commit
f4089ce
•
1 Parent(s): 368b66b

bloomz_bl_story

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. README.md +4 -4
  3. adapter_config.json +4 -6
  4. adapter_model.safetensors +2 -2
  5. runs/Apr11_03-48-59_321ddc84c049/events.out.tfevents.1712807923.321ddc84c049.145.0 +3 -0
  6. special_tokens_map.json +15 -4
  7. spiece.model +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +27 -10
  10. training_args.bin +1 -1
  11. wandb/debug-internal.log +108 -152
  12. wandb/debug.log +30 -30
  13. wandb/run-20240411_035909-21esl9hl/files/conda-environment.yaml +0 -0
  14. wandb/run-20240411_035909-21esl9hl/files/config.yaml +690 -0
  15. wandb/run-20240411_035909-21esl9hl/files/output.log +103 -0
  16. wandb/run-20240411_035909-21esl9hl/files/requirements.txt +864 -0
  17. wandb/run-20240411_035909-21esl9hl/files/wandb-metadata.json +66 -0
  18. wandb/run-20240411_035909-21esl9hl/files/wandb-summary.json +1 -0
  19. wandb/run-20240411_035909-21esl9hl/logs/debug-internal.log +118 -0
  20. wandb/run-20240411_035909-21esl9hl/logs/debug.log +32 -0
  21. wandb/run-20240411_035909-21esl9hl/run-21esl9hl.wandb +0 -0
.gitattributes CHANGED
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  wandb/run-20240408_203054-ldiuneeg/run-ldiuneeg.wandb filter=lfs diff=lfs merge=lfs -text
37
  wandb/run-20240410_010250-ft4a6i5j/run-ft4a6i5j.wandb filter=lfs diff=lfs merge=lfs -text
38
  wandb/run-20240410_115017-r9p6sok2/run-r9p6sok2.wandb filter=lfs diff=lfs merge=lfs -text
 
 
36
  wandb/run-20240408_203054-ldiuneeg/run-ldiuneeg.wandb filter=lfs diff=lfs merge=lfs -text
37
  wandb/run-20240410_010250-ft4a6i5j/run-ft4a6i5j.wandb filter=lfs diff=lfs merge=lfs -text
38
  wandb/run-20240410_115017-r9p6sok2/run-r9p6sok2.wandb filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,11 +1,11 @@
1
  ---
2
- license: mit
3
  library_name: peft
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: openai-community/gpt2-large
9
  model-index:
10
  - name: working
11
  results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # working
18
 
19
- This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on an unknown dataset.
20
 
21
  ## Model description
22
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.03
45
- - training_steps: 20
46
 
47
  ### Training results
48
 
 
1
  ---
2
+ license: bigscience-bloom-rail-1.0
3
  library_name: peft
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: bigscience/bloomz-560m
9
  model-index:
10
  - name: working
11
  results: []
 
16
 
17
  # working
18
 
19
+ This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
20
 
21
  ## Model description
22
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.03
45
+ - training_steps: 10
46
 
47
  ### Training results
48
 
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "openai-community/gpt2-large",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,11 +20,9 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "c_fc",
24
- "c_attn",
25
- "wte",
26
- "c_proj",
27
- "lm_head"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-560m",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "lm_head",
24
+ "query_key_value",
25
+ "dense_h_to_4h"
 
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e89a7e068c1b8ca512d8f84c288b20473c3e33b72af5e87dbdc4880c81fbaec5
3
- size 541561408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9baf0d7e0bee813113ef40ed93ff8433a426745af90937aabc260a737c8f5277
3
+ size 1042757704
runs/Apr11_03-48-59_321ddc84c049/events.out.tfevents.1712807923.321ddc84c049.145.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9ae83ebfcb3f35de03b0cb64494734931fec3a0f8dbe90d9f7ad0f502ddea5
3
+ size 15841
special_tokens_map.json CHANGED
@@ -1,6 +1,17 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": "</s>",
10
+ "unk_token": {
11
+ "content": "<unk>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
  }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,22 +1,39 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
- "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
- "eos_token": "<|endoftext|>",
 
16
  "max_length": 1024,
17
- "model_max_length": 1024,
18
- "pad_token": "<|endoftext|>",
19
- "tokenizer_class": "GPT2Tokenizer",
 
20
  "truncation": true,
21
- "unk_token": "<|endoftext|>"
22
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
  "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
29
  "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
  "max_length": 1024,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
  "truncation": true,
38
+ "unk_token": "<unk>"
39
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d336504ff1b5fa68adcdc85a42fecf652565e8aad52350e3bded9aa454938008
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fcb5d40d27446b473f3cf6a16217747341cc71590de85e4a2a9001a3be0bfca
3
  size 4920
wandb/debug-internal.log CHANGED
@@ -1,32 +1,32 @@
1
- 2024-04-11 01:01:03,983 INFO StreamThr :138 [internal.py:wandb_internal():86] W&B internal server running at pid: 138, started at: 2024-04-11 01:01:03.982415
2
- 2024-04-11 01:01:03,984 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status
3
- 2024-04-11 01:01:04,351 INFO WriterThread:138 [datastore.py:open_for_write():87] open: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/run-4b3fzolv.wandb
4
- 2024-04-11 01:01:04,352 DEBUG SenderThread:138 [sender.py:send():379] send: header
5
- 2024-04-11 01:01:04,355 DEBUG SenderThread:138 [sender.py:send():379] send: run
6
- 2024-04-11 01:01:04,503 INFO SenderThread:138 [dir_watcher.py:__init__():211] watching files in: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files
7
- 2024-04-11 01:01:04,503 INFO SenderThread:138 [sender.py:_start_run_threads():1124] run started: 4b3fzolv with start time 1712797263.984466
8
- 2024-04-11 01:01:04,511 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: check_version
9
- 2024-04-11 01:01:04,511 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: check_version
10
- 2024-04-11 01:01:04,599 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: run_start
11
- 2024-04-11 01:01:04,610 DEBUG HandlerThread:138 [system_info.py:__init__():26] System info init
12
- 2024-04-11 01:01:04,610 DEBUG HandlerThread:138 [system_info.py:__init__():41] System info init done
13
- 2024-04-11 01:01:04,610 INFO HandlerThread:138 [system_monitor.py:start():194] Starting system monitor
14
- 2024-04-11 01:01:04,610 INFO SystemMonitor:138 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
- 2024-04-11 01:01:04,610 INFO HandlerThread:138 [system_monitor.py:probe():214] Collecting system info
16
- 2024-04-11 01:01:04,611 INFO SystemMonitor:138 [interfaces.py:start():190] Started cpu monitoring
17
- 2024-04-11 01:01:04,611 INFO SystemMonitor:138 [interfaces.py:start():190] Started disk monitoring
18
- 2024-04-11 01:01:04,612 INFO SystemMonitor:138 [interfaces.py:start():190] Started gpu monitoring
19
- 2024-04-11 01:01:04,613 INFO SystemMonitor:138 [interfaces.py:start():190] Started memory monitoring
20
- 2024-04-11 01:01:04,614 INFO SystemMonitor:138 [interfaces.py:start():190] Started network monitoring
21
- 2024-04-11 01:01:04,623 DEBUG HandlerThread:138 [system_info.py:probe():150] Probing system
22
- 2024-04-11 01:01:04,625 DEBUG HandlerThread:138 [gitlib.py:_init_repo():56] git repository is invalid
23
- 2024-04-11 01:01:04,625 DEBUG HandlerThread:138 [system_info.py:probe():198] Probing system done
24
- 2024-04-11 01:01:04,626 DEBUG HandlerThread:138 [system_monitor.py:probe():223] {'os': 'Linux-5.15.133+-x86_64-with-glibc2.31', 'python': '3.10.13', 'heartbeatAt': '2024-04-11T01:01:04.623823', 'startedAt': '2024-04-11T01:01:03.976173', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'kaggle.ipynb', 'codePathLocal': None, 'root': '/kaggle/working', 'host': 'c072b7c9e487', 'username': 'root', 'executable': '/opt/conda/bin/python3.10', 'cpu_count': 2, 'cpu_count_logical': 4, 'cpu_freq': {'current': 2000.188, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2000.188, 'min': 0.0, 'max': 0.0}, {'current': 2000.188, 'min': 0.0, 'max': 0.0}, {'current': 2000.188, 'min': 0.0, 'max': 0.0}, {'current': 2000.188, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 8062.387607574463, 'used': 5566.689571380615}}, 'gpu': 'Tesla T4', 'gpu_count': 2, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}, {'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 31.357559204101562}}
25
- 2024-04-11 01:01:04,626 INFO HandlerThread:138 [system_monitor.py:probe():224] Finished collecting system info
26
- 2024-04-11 01:01:04,626 INFO HandlerThread:138 [system_monitor.py:probe():227] Publishing system info
27
- 2024-04-11 01:01:04,626 DEBUG HandlerThread:138 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
28
- 2024-04-11 01:01:05,505 INFO Thread-12 :138 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/conda-environment.yaml
29
- 2024-04-11 01:01:19,640 ERROR HandlerThread:138 [system_info.py:_save_conda():221] Error saving conda packages: Command '['conda', 'env', 'export']' timed out after 15 seconds
30
  Traceback (most recent call last):
31
  File "/opt/conda/lib/python3.10/site-packages/wandb/sdk/internal/system/system_info.py", line 214, in _save_conda
32
  subprocess.call(
@@ -37,126 +37,82 @@ Traceback (most recent call last):
37
  File "/opt/conda/lib/python3.10/subprocess.py", line 1951, in _wait
38
  raise TimeoutExpired(self.args, timeout)
39
  subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after 15 seconds
40
- 2024-04-11 01:01:19,643 DEBUG HandlerThread:138 [system_info.py:_save_conda():222] Saving conda packages done
41
- 2024-04-11 01:01:19,644 INFO HandlerThread:138 [system_monitor.py:probe():229] Finished publishing system info
42
- 2024-04-11 01:01:19,652 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
43
- 2024-04-11 01:01:19,652 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: keepalive
44
- 2024-04-11 01:01:19,652 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
45
- 2024-04-11 01:01:19,653 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: keepalive
46
- 2024-04-11 01:01:19,653 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
47
- 2024-04-11 01:01:19,653 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: keepalive
48
- 2024-04-11 01:01:19,653 DEBUG SenderThread:138 [sender.py:send():379] send: files
49
- 2024-04-11 01:01:19,653 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
50
- 2024-04-11 01:01:19,933 INFO wandb-upload_0:138 [upload_job.py:push():131] Uploaded file /tmp/tmpiqqv1dwfwandb/3d55vshp-wandb-metadata.json
51
- 2024-04-11 01:01:20,508 INFO Thread-12 :138 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/wandb-metadata.json
52
- 2024-04-11 01:01:20,599 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: python_packages
53
- 2024-04-11 01:01:20,599 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: python_packages
54
- 2024-04-11 01:01:20,602 DEBUG SenderThread:138 [sender.py:send():379] send: telemetry
55
- 2024-04-11 01:01:20,613 DEBUG SenderThread:138 [sender.py:send():379] send: config
56
- 2024-04-11 01:01:20,615 DEBUG SenderThread:138 [sender.py:send():379] send: metric
57
- 2024-04-11 01:01:20,615 DEBUG SenderThread:138 [sender.py:send():379] send: telemetry
58
- 2024-04-11 01:01:20,615 DEBUG SenderThread:138 [sender.py:send():379] send: metric
59
- 2024-04-11 01:01:20,615 WARNING SenderThread:138 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
60
- 2024-04-11 01:01:20,616 DEBUG SenderThread:138 [sender.py:send():379] send: telemetry
61
- 2024-04-11 01:01:20,616 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
62
- 2024-04-11 01:01:20,616 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
63
- 2024-04-11 01:01:20,617 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
64
- 2024-04-11 01:01:21,508 INFO Thread-12 :138 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/requirements.txt
65
- 2024-04-11 01:01:21,509 INFO Thread-12 :138 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/output.log
66
- 2024-04-11 01:01:23,509 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/output.log
67
- 2024-04-11 01:01:25,510 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/output.log
68
- 2024-04-11 01:01:25,513 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
69
- 2024-04-11 01:01:27,511 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/output.log
70
- 2024-04-11 01:01:30,790 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
71
- 2024-04-11 01:01:35,602 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
72
- 2024-04-11 01:01:35,603 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
73
- 2024-04-11 01:01:35,604 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
74
- 2024-04-11 01:01:36,648 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
75
- 2024-04-11 01:01:37,515 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/config.yaml
76
- 2024-04-11 01:01:41,766 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
77
- 2024-04-11 01:01:46,767 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
78
- 2024-04-11 01:01:50,600 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
79
- 2024-04-11 01:01:50,601 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
80
- 2024-04-11 01:01:50,640 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
81
- 2024-04-11 01:01:52,707 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
82
- 2024-04-11 01:01:57,708 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
83
- 2024-04-11 01:02:02,709 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
84
- 2024-04-11 01:02:04,614 DEBUG SystemMonitor:138 [system_monitor.py:_start():172] Starting system metrics aggregation loop
85
- 2024-04-11 01:02:04,616 DEBUG SenderThread:138 [sender.py:send():379] send: stats
86
- 2024-04-11 01:02:05,600 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
87
- 2024-04-11 01:02:05,601 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
88
- 2024-04-11 01:02:05,641 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
89
- 2024-04-11 01:02:08,651 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
90
- 2024-04-11 01:02:13,651 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
91
- 2024-04-11 01:02:18,652 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
92
- 2024-04-11 01:02:20,600 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
93
- 2024-04-11 01:02:20,601 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
94
- 2024-04-11 01:02:20,641 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
95
- 2024-04-11 01:02:23,671 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
96
- 2024-04-11 01:02:28,672 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
97
- 2024-04-11 01:02:33,673 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
98
- 2024-04-11 01:02:34,617 DEBUG SenderThread:138 [sender.py:send():379] send: stats
99
- 2024-04-11 01:02:35,601 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
100
- 2024-04-11 01:02:35,601 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
101
- 2024-04-11 01:02:35,641 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
102
- 2024-04-11 01:02:39,669 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
103
- 2024-04-11 01:02:44,669 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
104
- 2024-04-11 01:02:49,670 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
105
- 2024-04-11 01:02:50,601 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
106
- 2024-04-11 01:02:50,601 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
107
- 2024-04-11 01:02:50,641 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
108
- 2024-04-11 01:02:54,683 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
109
- 2024-04-11 01:02:59,684 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
110
- 2024-04-11 01:03:04,618 DEBUG SenderThread:138 [sender.py:send():379] send: stats
111
- 2024-04-11 01:03:05,601 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
112
- 2024-04-11 01:03:05,601 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
113
- 2024-04-11 01:03:05,641 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
114
- 2024-04-11 01:03:05,668 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
115
- 2024-04-11 01:03:10,669 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
116
- 2024-04-11 01:03:15,670 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
117
- 2024-04-11 01:03:20,601 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
118
- 2024-04-11 01:03:20,602 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
119
- 2024-04-11 01:03:20,641 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
120
- 2024-04-11 01:03:21,658 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
121
- 2024-04-11 01:03:26,659 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
122
- 2024-04-11 01:03:31,660 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
123
- 2024-04-11 01:03:34,619 DEBUG SenderThread:138 [sender.py:send():379] send: stats
124
- 2024-04-11 01:03:35,601 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
125
- 2024-04-11 01:03:35,602 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
126
- 2024-04-11 01:03:35,642 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
127
- 2024-04-11 01:03:36,661 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
128
- 2024-04-11 01:03:37,017 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: partial_history
129
- 2024-04-11 01:03:37,019 DEBUG SenderThread:138 [sender.py:send():379] send: metric
130
- 2024-04-11 01:03:37,019 DEBUG SenderThread:138 [sender.py:send():379] send: metric
131
- 2024-04-11 01:03:37,019 DEBUG SenderThread:138 [sender.py:send():379] send: metric
132
- 2024-04-11 01:03:37,020 DEBUG SenderThread:138 [sender.py:send():379] send: metric
133
- 2024-04-11 01:03:37,020 DEBUG SenderThread:138 [sender.py:send():379] send: history
134
- 2024-04-11 01:03:37,020 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
135
- 2024-04-11 01:03:37,020 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
136
- 2024-04-11 01:03:37,559 INFO Thread-12 :138 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/wandb-summary.json
137
- 2024-04-11 01:03:38,738 DEBUG SenderThread:138 [sender.py:send():379] send: telemetry
138
- 2024-04-11 01:03:38,738 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
139
- 2024-04-11 01:03:38,739 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: partial_history
140
- 2024-04-11 01:03:38,741 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
141
- 2024-04-11 01:03:38,741 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
142
- 2024-04-11 01:03:38,741 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
143
- 2024-04-11 01:03:38,742 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
144
- 2024-04-11 01:03:38,742 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
145
- 2024-04-11 01:03:38,742 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
146
- 2024-04-11 01:03:38,743 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
147
- 2024-04-11 01:03:38,743 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
148
- 2024-04-11 01:03:38,743 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
149
- 2024-04-11 01:03:38,744 DEBUG SenderThread:138 [sender.py:send():379] send: history
150
- 2024-04-11 01:03:38,744 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: summary_record
151
- 2024-04-11 01:03:38,744 INFO SenderThread:138 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
152
- 2024-04-11 01:03:39,559 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/wandb-summary.json
153
- 2024-04-11 01:03:39,560 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/output.log
154
- 2024-04-11 01:03:41,560 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/output.log
155
- 2024-04-11 01:03:41,871 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
156
- 2024-04-11 01:03:42,561 INFO Thread-12 :138 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_010103-4b3fzolv/files/config.yaml
157
- 2024-04-11 01:03:46,983 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
158
- 2024-04-11 01:03:50,601 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: stop_status
159
- 2024-04-11 01:03:50,602 DEBUG SenderThread:138 [sender.py:send_request():406] send_request: stop_status
160
- 2024-04-11 01:03:50,604 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: internal_messages
161
- 2024-04-11 01:03:52,705 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
162
- 2024-04-11 01:03:57,706 DEBUG HandlerThread:138 [handler.py:handle_request():146] handle_request: status_report
 
1
+ 2024-04-11 03:59:09,940 INFO StreamThr :191 [internal.py:wandb_internal():86] W&B internal server running at pid: 191, started at: 2024-04-11 03:59:09.939664
2
+ 2024-04-11 03:59:09,941 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status
3
+ 2024-04-11 03:59:10,363 INFO WriterThread:191 [datastore.py:open_for_write():87] open: /kaggle/working/wandb/run-20240411_035909-21esl9hl/run-21esl9hl.wandb
4
+ 2024-04-11 03:59:10,364 DEBUG SenderThread:191 [sender.py:send():379] send: header
5
+ 2024-04-11 03:59:10,367 DEBUG SenderThread:191 [sender.py:send():379] send: run
6
+ 2024-04-11 03:59:10,517 INFO SenderThread:191 [dir_watcher.py:__init__():211] watching files in: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files
7
+ 2024-04-11 03:59:10,517 INFO SenderThread:191 [sender.py:_start_run_threads():1124] run started: 21esl9hl with start time 1712807949.940735
8
+ 2024-04-11 03:59:10,526 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: check_version
9
+ 2024-04-11 03:59:10,526 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: check_version
10
+ 2024-04-11 03:59:10,621 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: run_start
11
+ 2024-04-11 03:59:10,635 DEBUG HandlerThread:191 [system_info.py:__init__():26] System info init
12
+ 2024-04-11 03:59:10,635 DEBUG HandlerThread:191 [system_info.py:__init__():41] System info init done
13
+ 2024-04-11 03:59:10,635 INFO HandlerThread:191 [system_monitor.py:start():194] Starting system monitor
14
+ 2024-04-11 03:59:10,635 INFO SystemMonitor:191 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
+ 2024-04-11 03:59:10,635 INFO HandlerThread:191 [system_monitor.py:probe():214] Collecting system info
16
+ 2024-04-11 03:59:10,639 INFO SystemMonitor:191 [interfaces.py:start():190] Started cpu monitoring
17
+ 2024-04-11 03:59:10,640 INFO SystemMonitor:191 [interfaces.py:start():190] Started disk monitoring
18
+ 2024-04-11 03:59:10,644 INFO SystemMonitor:191 [interfaces.py:start():190] Started gpu monitoring
19
+ 2024-04-11 03:59:10,644 INFO SystemMonitor:191 [interfaces.py:start():190] Started memory monitoring
20
+ 2024-04-11 03:59:10,645 INFO SystemMonitor:191 [interfaces.py:start():190] Started network monitoring
21
+ 2024-04-11 03:59:10,650 DEBUG HandlerThread:191 [system_info.py:probe():150] Probing system
22
+ 2024-04-11 03:59:10,652 DEBUG HandlerThread:191 [gitlib.py:_init_repo():56] git repository is invalid
23
+ 2024-04-11 03:59:10,652 DEBUG HandlerThread:191 [system_info.py:probe():198] Probing system done
24
+ 2024-04-11 03:59:10,652 DEBUG HandlerThread:191 [system_monitor.py:probe():223] {'os': 'Linux-5.15.133+-x86_64-with-glibc2.31', 'python': '3.10.13', 'heartbeatAt': '2024-04-11T03:59:10.650560', 'startedAt': '2024-04-11T03:59:09.933024', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'kaggle.ipynb', 'codePathLocal': None, 'root': '/kaggle/working', 'host': '321ddc84c049', 'username': 'root', 'executable': '/opt/conda/bin/python3.10', 'cpu_count': 2, 'cpu_count_logical': 4, 'cpu_freq': {'current': 2000.19, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2000.19, 'min': 0.0, 'max': 0.0}, {'current': 2000.19, 'min': 0.0, 'max': 0.0}, {'current': 2000.19, 'min': 0.0, 'max': 0.0}, {'current': 2000.19, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 8062.387607574463, 'used': 5566.961940765381}}, 'gpu': 'Tesla T4', 'gpu_count': 2, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}, {'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 31.357559204101562}}
25
+ 2024-04-11 03:59:10,653 INFO HandlerThread:191 [system_monitor.py:probe():224] Finished collecting system info
26
+ 2024-04-11 03:59:10,653 INFO HandlerThread:191 [system_monitor.py:probe():227] Publishing system info
27
+ 2024-04-11 03:59:10,653 DEBUG HandlerThread:191 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
28
+ 2024-04-11 03:59:11,520 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/conda-environment.yaml
29
+ 2024-04-11 03:59:25,667 ERROR HandlerThread:191 [system_info.py:_save_conda():221] Error saving conda packages: Command '['conda', 'env', 'export']' timed out after 15 seconds
30
  Traceback (most recent call last):
31
  File "/opt/conda/lib/python3.10/site-packages/wandb/sdk/internal/system/system_info.py", line 214, in _save_conda
32
  subprocess.call(
 
37
  File "/opt/conda/lib/python3.10/subprocess.py", line 1951, in _wait
38
  raise TimeoutExpired(self.args, timeout)
39
  subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after 15 seconds
40
+ 2024-04-11 03:59:25,670 DEBUG HandlerThread:191 [system_info.py:_save_conda():222] Saving conda packages done
41
+ 2024-04-11 03:59:25,671 INFO HandlerThread:191 [system_monitor.py:probe():229] Finished publishing system info
42
+ 2024-04-11 03:59:25,678 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
43
+ 2024-04-11 03:59:25,678 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: keepalive
44
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
45
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: keepalive
46
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
47
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: keepalive
48
+ 2024-04-11 03:59:25,679 DEBUG SenderThread:191 [sender.py:send():379] send: files
49
+ 2024-04-11 03:59:25,680 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
50
+ 2024-04-11 03:59:25,883 INFO wandb-upload_0:191 [upload_job.py:push():131] Uploaded file /tmp/tmpgmb8demxwandb/zh9coxtl-wandb-metadata.json
51
+ 2024-04-11 03:59:26,522 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/wandb-metadata.json
52
+ 2024-04-11 03:59:26,714 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: python_packages
53
+ 2024-04-11 03:59:26,714 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: python_packages
54
+ 2024-04-11 03:59:26,717 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
55
+ 2024-04-11 03:59:26,727 DEBUG SenderThread:191 [sender.py:send():379] send: config
56
+ 2024-04-11 03:59:26,728 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
57
+ 2024-04-11 03:59:26,729 DEBUG SenderThread:191 [sender.py:send():379] send: metric
58
+ 2024-04-11 03:59:26,729 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
59
+ 2024-04-11 03:59:26,730 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
60
+ 2024-04-11 03:59:26,731 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
61
+ 2024-04-11 03:59:26,776 DEBUG SenderThread:191 [sender.py:send():379] send: metric
62
+ 2024-04-11 03:59:26,776 WARNING SenderThread:191 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
63
+ 2024-04-11 03:59:26,776 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
64
+ 2024-04-11 03:59:27,522 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/requirements.txt
65
+ 2024-04-11 03:59:27,523 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
66
+ 2024-04-11 03:59:29,523 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
67
+ 2024-04-11 03:59:30,951 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
68
+ 2024-04-11 03:59:31,524 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
69
+ 2024-04-11 03:59:33,525 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
70
+ 2024-04-11 03:59:35,952 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
71
+ 2024-04-11 03:59:40,958 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
72
+ 2024-04-11 03:59:41,528 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/config.yaml
73
+ 2024-04-11 03:59:41,717 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
74
+ 2024-04-11 03:59:41,717 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
75
+ 2024-04-11 03:59:41,718 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
76
+ 2024-04-11 03:59:45,530 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
77
+ 2024-04-11 03:59:46,261 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
78
+ 2024-04-11 03:59:51,262 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
79
+ 2024-04-11 03:59:56,417 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
80
+ 2024-04-11 03:59:56,717 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
81
+ 2024-04-11 03:59:56,718 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
82
+ 2024-04-11 03:59:56,719 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
83
+ 2024-04-11 03:59:57,534 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
84
+ 2024-04-11 04:00:01,827 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
85
+ 2024-04-11 04:00:06,828 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
86
+ 2024-04-11 04:00:08,943 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
87
+ 2024-04-11 04:00:08,983 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: partial_history
88
+ 2024-04-11 04:00:08,985 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
89
+ 2024-04-11 04:00:08,988 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
90
+ 2024-04-11 04:00:08,988 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
91
+ 2024-04-11 04:00:08,989 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
92
+ 2024-04-11 04:00:08,989 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
93
+ 2024-04-11 04:00:08,989 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
94
+ 2024-04-11 04:00:08,989 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
95
+ 2024-04-11 04:00:08,990 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
96
+ 2024-04-11 04:00:08,990 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
97
+ 2024-04-11 04:00:08,990 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
98
+ 2024-04-11 04:00:08,990 DEBUG SenderThread:191 [sender.py:send():379] send: metric
99
+ 2024-04-11 04:00:08,991 DEBUG SenderThread:191 [sender.py:send():379] send: history
100
+ 2024-04-11 04:00:08,991 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
101
+ 2024-04-11 04:00:08,991 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
102
+ 2024-04-11 04:00:09,539 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/wandb-summary.json
103
+ 2024-04-11 04:00:10,645 DEBUG SystemMonitor:191 [system_monitor.py:_start():172] Starting system metrics aggregation loop
104
+ 2024-04-11 04:00:10,647 DEBUG SenderThread:191 [sender.py:send():379] send: stats
105
+ 2024-04-11 04:00:11,539 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
106
+ 2024-04-11 04:00:11,715 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
107
+ 2024-04-11 04:00:11,716 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
108
+ 2024-04-11 04:00:11,719 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
109
+ 2024-04-11 04:00:11,833 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
110
+ 2024-04-11 04:00:12,540 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/config.yaml
111
+ 2024-04-11 04:00:16,925 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
112
+ 2024-04-11 04:00:21,926 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
113
+ 2024-04-11 04:00:26,716 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
114
+ 2024-04-11 04:00:26,716 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
115
+ 2024-04-11 04:00:26,757 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
116
+ 2024-04-11 04:00:27,786 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
117
+ 2024-04-11 04:00:32,787 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
118
+ 2024-04-11 04:00:37,788 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wandb/debug.log CHANGED
@@ -1,32 +1,32 @@
1
- 2024-04-11 01:01:03,977 INFO MainThread:94 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
2
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Configure stats pid to 94
3
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
5
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Applying login settings: {}
9
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
10
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240411_010103-4b3fzolv/logs/debug.log
11
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240411_010103-4b3fzolv/logs/debug-internal.log
12
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7bfd48105450>
13
- 2024-04-11 01:01:03,978 INFO MainThread:94 [wandb_init.py:init():567] calling init triggers
14
- 2024-04-11 01:01:03,979 INFO MainThread:94 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
15
  config: {}
16
- 2024-04-11 01:01:03,979 INFO MainThread:94 [wandb_init.py:init():617] starting backend
17
- 2024-04-11 01:01:03,979 INFO MainThread:94 [wandb_init.py:init():621] setting up manager
18
- 2024-04-11 01:01:03,980 INFO MainThread:94 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
19
- 2024-04-11 01:01:03,984 INFO MainThread:94 [wandb_init.py:init():629] backend started and connected
20
- 2024-04-11 01:01:03,997 INFO MainThread:94 [wandb_run.py:_label_probe_notebook():1299] probe notebook
21
- 2024-04-11 01:01:04,350 INFO MainThread:94 [wandb_init.py:init():721] updated telemetry
22
- 2024-04-11 01:01:04,354 INFO MainThread:94 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
23
- 2024-04-11 01:01:04,510 INFO MainThread:94 [wandb_run.py:_on_init():2344] communicating current version
24
- 2024-04-11 01:01:04,593 INFO MainThread:94 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
25
 
26
- 2024-04-11 01:01:04,593 INFO MainThread:94 [wandb_init.py:init():805] starting run threads in backend
27
- 2024-04-11 01:01:20,600 INFO MainThread:94 [wandb_run.py:_console_start():2323] atexit reg
28
- 2024-04-11 01:01:20,600 INFO MainThread:94 [wandb_run.py:_redirect():2178] redirect: wrap_raw
29
- 2024-04-11 01:01:20,601 INFO MainThread:94 [wandb_run.py:_redirect():2243] Wrapping output streams.
30
- 2024-04-11 01:01:20,601 INFO MainThread:94 [wandb_run.py:_redirect():2268] Redirects installed.
31
- 2024-04-11 01:01:20,602 INFO MainThread:94 [wandb_init.py:init():848] run started, returning control to user process
32
- 2024-04-11 01:01:20,608 INFO MainThread:94 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 50257, 'n_positions': 1024, 'n_embd': 1280, 'n_layer': 36, 'n_head': 20, 'n_inner': None, 'activation_function': 'gelu_new', 'resid_pdrop': 0.1, 'embd_pdrop': 0.1, 'attn_pdrop': 0.1, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'summary_type': 'cls_index', 'summary_use_proj': True, 'summary_activation': None, 'summary_first_dropout': 0.1, 'summary_proj_to_labels': True, 'scale_attn_weights': True, 'use_cache': False, 'scale_attn_by_inverse_layer_idx': False, 'reorder_and_upcast_attn': False, 'bos_token_id': 50256, 'eos_token_id': 50256, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['GPT2LMHeadModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': {'text-generation': {'do_sample': True, 'max_length': 50}}, 'problem_type': None, '_name_or_path': 'openai-community/gpt2-large', 'transformers_version': '4.39.3', 'model_type': 'gpt2', 'n_ctx': 1024, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': False, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 20, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr11_00-59-48_c072b7c9e487', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 8, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': True, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
 
1
+ 2024-04-11 03:59:09,934 INFO MainThread:145 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
2
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Configure stats pid to 145
3
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
5
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Applying login settings: {}
9
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
10
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240411_035909-21esl9hl/logs/debug.log
11
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240411_035909-21esl9hl/logs/debug-internal.log
12
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7e1d3f588970>
13
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():567] calling init triggers
14
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
15
  config: {}
16
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():617] starting backend
17
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():621] setting up manager
18
+ 2024-04-11 03:59:09,938 INFO MainThread:145 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
19
+ 2024-04-11 03:59:09,940 INFO MainThread:145 [wandb_init.py:init():629] backend started and connected
20
+ 2024-04-11 03:59:09,953 INFO MainThread:145 [wandb_run.py:_label_probe_notebook():1299] probe notebook
21
+ 2024-04-11 03:59:10,362 INFO MainThread:145 [wandb_init.py:init():721] updated telemetry
22
+ 2024-04-11 03:59:10,366 INFO MainThread:145 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
23
+ 2024-04-11 03:59:10,526 INFO MainThread:145 [wandb_run.py:_on_init():2344] communicating current version
24
+ 2024-04-11 03:59:10,613 INFO MainThread:145 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
25
 
26
+ 2024-04-11 03:59:10,614 INFO MainThread:145 [wandb_init.py:init():805] starting run threads in backend
27
+ 2024-04-11 03:59:26,715 INFO MainThread:145 [wandb_run.py:_console_start():2323] atexit reg
28
+ 2024-04-11 03:59:26,715 INFO MainThread:145 [wandb_run.py:_redirect():2178] redirect: wrap_raw
29
+ 2024-04-11 03:59:26,716 INFO MainThread:145 [wandb_run.py:_redirect():2243] Wrapping output streams.
30
+ 2024-04-11 03:59:26,716 INFO MainThread:145 [wandb_run.py:_redirect():2268] Redirects installed.
31
+ 2024-04-11 03:59:26,717 INFO MainThread:145 [wandb_init.py:init():848] run started, returning control to user process
32
+ 2024-04-11 03:59:26,723 INFO MainThread:145 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1024, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-560m', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': False, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 10, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr11_03-48-59_321ddc84c049', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 8, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': True, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
wandb/run-20240411_035909-21esl9hl/files/conda-environment.yaml ADDED
File without changes
wandb/run-20240411_035909-21esl9hl/files/config.yaml ADDED
@@ -0,0 +1,690 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.10.13
7
+ cli_version: 0.16.5
8
+ framework: huggingface
9
+ huggingface_version: 4.39.3
10
+ is_jupyter_run: true
11
+ is_kaggle_kernel: true
12
+ start_time: 1712807949.0
13
+ t:
14
+ 1:
15
+ - 1
16
+ - 2
17
+ - 3
18
+ - 5
19
+ - 11
20
+ - 12
21
+ - 49
22
+ - 51
23
+ - 53
24
+ - 55
25
+ - 71
26
+ - 84
27
+ - 98
28
+ - 105
29
+ 2:
30
+ - 1
31
+ - 2
32
+ - 3
33
+ - 5
34
+ - 11
35
+ - 12
36
+ - 49
37
+ - 51
38
+ - 53
39
+ - 55
40
+ - 71
41
+ - 84
42
+ - 98
43
+ - 105
44
+ 3:
45
+ - 7
46
+ - 23
47
+ - 62
48
+ 4: 3.10.13
49
+ 5: 0.16.5
50
+ 6: 4.39.3
51
+ 8:
52
+ - 1
53
+ - 2
54
+ - 5
55
+ 9:
56
+ 1: transformers_trainer
57
+ 13: linux-x86_64
58
+ m:
59
+ - 1: train/global_step
60
+ 6:
61
+ - 3
62
+ - 1: train/epoch
63
+ 5: 1
64
+ 6:
65
+ - 1
66
+ vocab_size:
67
+ desc: null
68
+ value: 250880
69
+ hidden_size:
70
+ desc: null
71
+ value: 1024
72
+ n_layer:
73
+ desc: null
74
+ value: 24
75
+ n_head:
76
+ desc: null
77
+ value: 16
78
+ layer_norm_epsilon:
79
+ desc: null
80
+ value: 1.0e-05
81
+ initializer_range:
82
+ desc: null
83
+ value: 0.02
84
+ use_cache:
85
+ desc: null
86
+ value: false
87
+ pretraining_tp:
88
+ desc: null
89
+ value: 1
90
+ apply_residual_connection_post_layernorm:
91
+ desc: null
92
+ value: false
93
+ hidden_dropout:
94
+ desc: null
95
+ value: 0.0
96
+ attention_dropout:
97
+ desc: null
98
+ value: 0.0
99
+ bos_token_id:
100
+ desc: null
101
+ value: 1
102
+ eos_token_id:
103
+ desc: null
104
+ value: 2
105
+ slow_but_exact:
106
+ desc: null
107
+ value: false
108
+ return_dict:
109
+ desc: null
110
+ value: true
111
+ output_hidden_states:
112
+ desc: null
113
+ value: false
114
+ output_attentions:
115
+ desc: null
116
+ value: false
117
+ torchscript:
118
+ desc: null
119
+ value: false
120
+ torch_dtype:
121
+ desc: null
122
+ value: null
123
+ use_bfloat16:
124
+ desc: null
125
+ value: false
126
+ tf_legacy_loss:
127
+ desc: null
128
+ value: false
129
+ pruned_heads:
130
+ desc: null
131
+ value: {}
132
+ tie_word_embeddings:
133
+ desc: null
134
+ value: true
135
+ chunk_size_feed_forward:
136
+ desc: null
137
+ value: 0
138
+ is_encoder_decoder:
139
+ desc: null
140
+ value: false
141
+ is_decoder:
142
+ desc: null
143
+ value: false
144
+ cross_attention_hidden_size:
145
+ desc: null
146
+ value: null
147
+ add_cross_attention:
148
+ desc: null
149
+ value: false
150
+ tie_encoder_decoder:
151
+ desc: null
152
+ value: false
153
+ max_length:
154
+ desc: null
155
+ value: 20
156
+ min_length:
157
+ desc: null
158
+ value: 0
159
+ do_sample:
160
+ desc: null
161
+ value: false
162
+ early_stopping:
163
+ desc: null
164
+ value: false
165
+ num_beams:
166
+ desc: null
167
+ value: 1
168
+ num_beam_groups:
169
+ desc: null
170
+ value: 1
171
+ diversity_penalty:
172
+ desc: null
173
+ value: 0.0
174
+ temperature:
175
+ desc: null
176
+ value: 1.0
177
+ top_k:
178
+ desc: null
179
+ value: 50
180
+ top_p:
181
+ desc: null
182
+ value: 1.0
183
+ typical_p:
184
+ desc: null
185
+ value: 1.0
186
+ repetition_penalty:
187
+ desc: null
188
+ value: 1.0
189
+ length_penalty:
190
+ desc: null
191
+ value: 1.0
192
+ no_repeat_ngram_size:
193
+ desc: null
194
+ value: 0
195
+ encoder_no_repeat_ngram_size:
196
+ desc: null
197
+ value: 0
198
+ bad_words_ids:
199
+ desc: null
200
+ value: null
201
+ num_return_sequences:
202
+ desc: null
203
+ value: 1
204
+ output_scores:
205
+ desc: null
206
+ value: false
207
+ return_dict_in_generate:
208
+ desc: null
209
+ value: false
210
+ forced_bos_token_id:
211
+ desc: null
212
+ value: null
213
+ forced_eos_token_id:
214
+ desc: null
215
+ value: null
216
+ remove_invalid_values:
217
+ desc: null
218
+ value: false
219
+ exponential_decay_length_penalty:
220
+ desc: null
221
+ value: null
222
+ suppress_tokens:
223
+ desc: null
224
+ value: null
225
+ begin_suppress_tokens:
226
+ desc: null
227
+ value: null
228
+ architectures:
229
+ desc: null
230
+ value:
231
+ - BloomForCausalLM
232
+ finetuning_task:
233
+ desc: null
234
+ value: null
235
+ id2label:
236
+ desc: null
237
+ value:
238
+ '0': LABEL_0
239
+ '1': LABEL_1
240
+ label2id:
241
+ desc: null
242
+ value:
243
+ LABEL_0: 0
244
+ LABEL_1: 1
245
+ tokenizer_class:
246
+ desc: null
247
+ value: null
248
+ prefix:
249
+ desc: null
250
+ value: null
251
+ pad_token_id:
252
+ desc: null
253
+ value: 3
254
+ sep_token_id:
255
+ desc: null
256
+ value: null
257
+ decoder_start_token_id:
258
+ desc: null
259
+ value: null
260
+ task_specific_params:
261
+ desc: null
262
+ value: null
263
+ problem_type:
264
+ desc: null
265
+ value: null
266
+ _name_or_path:
267
+ desc: null
268
+ value: bigscience/bloomz-560m
269
+ transformers_version:
270
+ desc: null
271
+ value: 4.39.3
272
+ attention_softmax_in_fp32:
273
+ desc: null
274
+ value: true
275
+ bias_dropout_fusion:
276
+ desc: null
277
+ value: true
278
+ unk_token_id:
279
+ desc: null
280
+ value: 0
281
+ masked_softmax_fusion:
282
+ desc: null
283
+ value: true
284
+ model_type:
285
+ desc: null
286
+ value: bloom
287
+ n_inner:
288
+ desc: null
289
+ value: null
290
+ offset_alibi:
291
+ desc: null
292
+ value: 100
293
+ seq_length:
294
+ desc: null
295
+ value: 2048
296
+ skip_bias_add:
297
+ desc: null
298
+ value: true
299
+ skip_bias_add_qkv:
300
+ desc: null
301
+ value: false
302
+ quantization_config:
303
+ desc: null
304
+ value:
305
+ quant_method: QuantizationMethod.BITS_AND_BYTES
306
+ _load_in_8bit: false
307
+ _load_in_4bit: true
308
+ llm_int8_threshold: 6.0
309
+ llm_int8_skip_modules: null
310
+ llm_int8_enable_fp32_cpu_offload: false
311
+ llm_int8_has_fp16_weight: false
312
+ bnb_4bit_quant_type: nf4
313
+ bnb_4bit_use_double_quant: false
314
+ bnb_4bit_compute_dtype: float16
315
+ bnb_4bit_quant_storage: uint8
316
+ load_in_4bit: true
317
+ load_in_8bit: false
318
+ output_dir:
319
+ desc: null
320
+ value: /kaggle/working/
321
+ overwrite_output_dir:
322
+ desc: null
323
+ value: false
324
+ do_train:
325
+ desc: null
326
+ value: false
327
+ do_eval:
328
+ desc: null
329
+ value: false
330
+ do_predict:
331
+ desc: null
332
+ value: false
333
+ evaluation_strategy:
334
+ desc: null
335
+ value: 'no'
336
+ prediction_loss_only:
337
+ desc: null
338
+ value: false
339
+ per_device_train_batch_size:
340
+ desc: null
341
+ value: 8
342
+ per_device_eval_batch_size:
343
+ desc: null
344
+ value: 8
345
+ per_gpu_train_batch_size:
346
+ desc: null
347
+ value: null
348
+ per_gpu_eval_batch_size:
349
+ desc: null
350
+ value: null
351
+ gradient_accumulation_steps:
352
+ desc: null
353
+ value: 1
354
+ eval_accumulation_steps:
355
+ desc: null
356
+ value: null
357
+ eval_delay:
358
+ desc: null
359
+ value: 0
360
+ learning_rate:
361
+ desc: null
362
+ value: 3.0e-05
363
+ weight_decay:
364
+ desc: null
365
+ value: 0.0001
366
+ adam_beta1:
367
+ desc: null
368
+ value: 0.9
369
+ adam_beta2:
370
+ desc: null
371
+ value: 0.999
372
+ adam_epsilon:
373
+ desc: null
374
+ value: 1.0e-08
375
+ max_grad_norm:
376
+ desc: null
377
+ value: 0.3
378
+ num_train_epochs:
379
+ desc: null
380
+ value: 5
381
+ max_steps:
382
+ desc: null
383
+ value: 10
384
+ lr_scheduler_type:
385
+ desc: null
386
+ value: cosine
387
+ lr_scheduler_kwargs:
388
+ desc: null
389
+ value: {}
390
+ warmup_ratio:
391
+ desc: null
392
+ value: 0.03
393
+ warmup_steps:
394
+ desc: null
395
+ value: 0
396
+ log_level:
397
+ desc: null
398
+ value: passive
399
+ log_level_replica:
400
+ desc: null
401
+ value: warning
402
+ log_on_each_node:
403
+ desc: null
404
+ value: true
405
+ logging_dir:
406
+ desc: null
407
+ value: /kaggle/working/runs/Apr11_03-48-59_321ddc84c049
408
+ logging_strategy:
409
+ desc: null
410
+ value: steps
411
+ logging_first_step:
412
+ desc: null
413
+ value: false
414
+ logging_steps:
415
+ desc: null
416
+ value: 20
417
+ logging_nan_inf_filter:
418
+ desc: null
419
+ value: true
420
+ save_strategy:
421
+ desc: null
422
+ value: steps
423
+ save_steps:
424
+ desc: null
425
+ value: 20
426
+ save_total_limit:
427
+ desc: null
428
+ value: 1
429
+ save_safetensors:
430
+ desc: null
431
+ value: true
432
+ save_on_each_node:
433
+ desc: null
434
+ value: false
435
+ save_only_model:
436
+ desc: null
437
+ value: false
438
+ no_cuda:
439
+ desc: null
440
+ value: false
441
+ use_cpu:
442
+ desc: null
443
+ value: false
444
+ use_mps_device:
445
+ desc: null
446
+ value: false
447
+ seed:
448
+ desc: null
449
+ value: 42
450
+ data_seed:
451
+ desc: null
452
+ value: null
453
+ jit_mode_eval:
454
+ desc: null
455
+ value: false
456
+ use_ipex:
457
+ desc: null
458
+ value: false
459
+ bf16:
460
+ desc: null
461
+ value: false
462
+ fp16:
463
+ desc: null
464
+ value: false
465
+ fp16_opt_level:
466
+ desc: null
467
+ value: O1
468
+ half_precision_backend:
469
+ desc: null
470
+ value: auto
471
+ bf16_full_eval:
472
+ desc: null
473
+ value: false
474
+ fp16_full_eval:
475
+ desc: null
476
+ value: false
477
+ tf32:
478
+ desc: null
479
+ value: null
480
+ local_rank:
481
+ desc: null
482
+ value: 0
483
+ ddp_backend:
484
+ desc: null
485
+ value: null
486
+ tpu_num_cores:
487
+ desc: null
488
+ value: null
489
+ tpu_metrics_debug:
490
+ desc: null
491
+ value: false
492
+ debug:
493
+ desc: null
494
+ value: []
495
+ dataloader_drop_last:
496
+ desc: null
497
+ value: false
498
+ eval_steps:
499
+ desc: null
500
+ value: null
501
+ dataloader_num_workers:
502
+ desc: null
503
+ value: 8
504
+ dataloader_prefetch_factor:
505
+ desc: null
506
+ value: null
507
+ past_index:
508
+ desc: null
509
+ value: -1
510
+ run_name:
511
+ desc: null
512
+ value: /kaggle/working/
513
+ disable_tqdm:
514
+ desc: null
515
+ value: false
516
+ remove_unused_columns:
517
+ desc: null
518
+ value: true
519
+ label_names:
520
+ desc: null
521
+ value: null
522
+ load_best_model_at_end:
523
+ desc: null
524
+ value: false
525
+ metric_for_best_model:
526
+ desc: null
527
+ value: null
528
+ greater_is_better:
529
+ desc: null
530
+ value: null
531
+ ignore_data_skip:
532
+ desc: null
533
+ value: false
534
+ fsdp:
535
+ desc: null
536
+ value: []
537
+ fsdp_min_num_params:
538
+ desc: null
539
+ value: 0
540
+ fsdp_config:
541
+ desc: null
542
+ value:
543
+ min_num_params: 0
544
+ xla: false
545
+ xla_fsdp_v2: false
546
+ xla_fsdp_grad_ckpt: false
547
+ fsdp_transformer_layer_cls_to_wrap:
548
+ desc: null
549
+ value: null
550
+ accelerator_config:
551
+ desc: null
552
+ value:
553
+ split_batches: false
554
+ dispatch_batches: null
555
+ even_batches: true
556
+ use_seedable_sampler: true
557
+ deepspeed:
558
+ desc: null
559
+ value: null
560
+ label_smoothing_factor:
561
+ desc: null
562
+ value: 0.0
563
+ optim:
564
+ desc: null
565
+ value: paged_adamw_32bit
566
+ optim_args:
567
+ desc: null
568
+ value: null
569
+ adafactor:
570
+ desc: null
571
+ value: false
572
+ group_by_length:
573
+ desc: null
574
+ value: false
575
+ length_column_name:
576
+ desc: null
577
+ value: length
578
+ report_to:
579
+ desc: null
580
+ value:
581
+ - tensorboard
582
+ - wandb
583
+ ddp_find_unused_parameters:
584
+ desc: null
585
+ value: null
586
+ ddp_bucket_cap_mb:
587
+ desc: null
588
+ value: null
589
+ ddp_broadcast_buffers:
590
+ desc: null
591
+ value: null
592
+ dataloader_pin_memory:
593
+ desc: null
594
+ value: true
595
+ dataloader_persistent_workers:
596
+ desc: null
597
+ value: false
598
+ skip_memory_metrics:
599
+ desc: null
600
+ value: true
601
+ use_legacy_prediction_loop:
602
+ desc: null
603
+ value: false
604
+ push_to_hub:
605
+ desc: null
606
+ value: false
607
+ resume_from_checkpoint:
608
+ desc: null
609
+ value: null
610
+ hub_model_id:
611
+ desc: null
612
+ value: null
613
+ hub_strategy:
614
+ desc: null
615
+ value: every_save
616
+ hub_token:
617
+ desc: null
618
+ value: <HUB_TOKEN>
619
+ hub_private_repo:
620
+ desc: null
621
+ value: false
622
+ hub_always_push:
623
+ desc: null
624
+ value: false
625
+ gradient_checkpointing:
626
+ desc: null
627
+ value: true
628
+ gradient_checkpointing_kwargs:
629
+ desc: null
630
+ value: null
631
+ include_inputs_for_metrics:
632
+ desc: null
633
+ value: false
634
+ fp16_backend:
635
+ desc: null
636
+ value: auto
637
+ push_to_hub_model_id:
638
+ desc: null
639
+ value: null
640
+ push_to_hub_organization:
641
+ desc: null
642
+ value: null
643
+ push_to_hub_token:
644
+ desc: null
645
+ value: <PUSH_TO_HUB_TOKEN>
646
+ mp_parameters:
647
+ desc: null
648
+ value: ''
649
+ auto_find_batch_size:
650
+ desc: null
651
+ value: true
652
+ full_determinism:
653
+ desc: null
654
+ value: false
655
+ torchdynamo:
656
+ desc: null
657
+ value: null
658
+ ray_scope:
659
+ desc: null
660
+ value: last
661
+ ddp_timeout:
662
+ desc: null
663
+ value: 1800
664
+ torch_compile:
665
+ desc: null
666
+ value: false
667
+ torch_compile_backend:
668
+ desc: null
669
+ value: null
670
+ torch_compile_mode:
671
+ desc: null
672
+ value: null
673
+ dispatch_batches:
674
+ desc: null
675
+ value: null
676
+ split_batches:
677
+ desc: null
678
+ value: null
679
+ include_tokens_per_second:
680
+ desc: null
681
+ value: false
682
+ include_num_input_tokens_seen:
683
+ desc: null
684
+ value: false
685
+ neftune_noise_alpha:
686
+ desc: null
687
+ value: null
688
+ optim_target_modules:
689
+ desc: null
690
+ value: null
wandb/run-20240411_035909-21esl9hl/files/output.log ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /opt/conda/lib/python3.10/site-packages/torch/utils/data/dataloader.py:557: UserWarning: This DataLoader will create 8 worker processes in total. Our suggested max number of worker in current system is 4, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
2
+ warnings.warn(_create_warning_msg(
3
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
4
+ To disable this warning, you can either:
5
+ - Avoid using `tokenizers` before the fork if possible
6
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
7
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
8
+ To disable this warning, you can either:
9
+ - Avoid using `tokenizers` before the fork if possible
10
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
11
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
12
+ To disable this warning, you can either:
13
+ - Avoid using `tokenizers` before the fork if possible
14
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
15
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
16
+ To disable this warning, you can either:
17
+ - Avoid using `tokenizers` before the fork if possible
18
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
19
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
20
+ To disable this warning, you can either:
21
+ - Avoid using `tokenizers` before the fork if possible
22
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
23
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
24
+ To disable this warning, you can either:
25
+ - Avoid using `tokenizers` before the fork if possible
26
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
27
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
28
+ To disable this warning, you can either:
29
+ - Avoid using `tokenizers` before the fork if possible
30
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
31
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
32
+ To disable this warning, you can either:
33
+ - Avoid using `tokenizers` before the fork if possible
34
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
35
+ /opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
36
+ warnings.warn(
37
+ /opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
38
+ warnings.warn('Was asked to gather along dimension 0, but all '
39
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
40
+ To disable this warning, you can either:
41
+ - Avoid using `tokenizers` before the fork if possible
42
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
43
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
44
+ To disable this warning, you can either:
45
+ - Avoid using `tokenizers` before the fork if possible
46
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
47
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
48
+ To disable this warning, you can either:
49
+ - Avoid using `tokenizers` before the fork if possible
50
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
51
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
52
+ To disable this warning, you can either:
53
+ - Avoid using `tokenizers` before the fork if possible
54
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
55
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
56
+ To disable this warning, you can either:
57
+ - Avoid using `tokenizers` before the fork if possible
58
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
59
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
60
+ To disable this warning, you can either:
61
+ - Avoid using `tokenizers` before the fork if possible
62
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
63
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
64
+ To disable this warning, you can either:
65
+ - Avoid using `tokenizers` before the fork if possible
66
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
67
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
68
+ To disable this warning, you can either:
69
+ - Avoid using `tokenizers` before the fork if possible
70
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
71
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
72
+ To disable this warning, you can either:
73
+ - Avoid using `tokenizers` before the fork if possible
74
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
75
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
76
+ To disable this warning, you can either:
77
+ - Avoid using `tokenizers` before the fork if possible
78
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
79
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
80
+ To disable this warning, you can either:
81
+ - Avoid using `tokenizers` before the fork if possible
82
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
83
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
84
+ To disable this warning, you can either:
85
+ - Avoid using `tokenizers` before the fork if possible
86
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
87
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
88
+ To disable this warning, you can either:
89
+ - Avoid using `tokenizers` before the fork if possible
90
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
91
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
92
+ To disable this warning, you can either:
93
+ - Avoid using `tokenizers` before the fork if possible
94
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
95
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
96
+ To disable this warning, you can either:
97
+ - Avoid using `tokenizers` before the fork if possible
98
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
99
+ huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
100
+ To disable this warning, you can either:
101
+ - Avoid using `tokenizers` before the fork if possible
102
+ - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
103
+ /opt/conda/lib/python3.10/site-packages/peft/utils/save_and_load.py:139: UserWarning: Setting `save_embedding_layers` to `True` as embedding layers found in `target_modules`.
wandb/run-20240411_035909-21esl9hl/files/requirements.txt ADDED
@@ -0,0 +1,864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Babel==2.14.0
2
+ Boruta==0.3
3
+ Brotli==1.0.9
4
+ CVXcanon==0.1.2
5
+ Cartopy==0.22.0
6
+ Cython==3.0.8
7
+ Deprecated==1.2.14
8
+ Farama-Notifications==0.0.4
9
+ Flask==3.0.2
10
+ Geohash==1.0
11
+ GitPython==3.1.41
12
+ ImageHash==4.3.1
13
+ Janome==0.5.0
14
+ Jinja2==3.1.2
15
+ LunarCalendar==0.0.9
16
+ Mako==1.3.2
17
+ Markdown==3.5.2
18
+ MarkupSafe==2.1.3
19
+ MarkupSafe==2.1.5
20
+ Pillow==9.5.0
21
+ PuLP==2.8.0
22
+ PyArabic==0.6.15
23
+ PyJWT==2.8.0
24
+ PyMeeus==0.5.12
25
+ PySocks==1.7.1
26
+ PyUpSet==0.1.1.post7
27
+ PyWavelets==1.5.0
28
+ PyYAML==6.0.1
29
+ Pygments==2.17.2
30
+ Pympler==1.0.1
31
+ QtPy==2.4.1
32
+ Rtree==1.2.0
33
+ SQLAlchemy==2.0.25
34
+ SecretStorage==3.3.3
35
+ Send2Trash==1.8.2
36
+ Shapely==1.8.5.post1
37
+ Shimmy==1.3.0
38
+ SimpleITK==2.3.1
39
+ TPOT==0.12.1
40
+ Theano-PyMC==1.1.2
41
+ Theano==1.0.5
42
+ Wand==0.6.13
43
+ Werkzeug==3.0.2
44
+ absl-py==1.4.0
45
+ accelerate==0.28.0
46
+ access==1.1.9
47
+ affine==2.4.0
48
+ aiobotocore==2.12.2
49
+ aiofiles==22.1.0
50
+ aiohttp-cors==0.7.0
51
+ aiohttp==3.9.1
52
+ aioitertools==0.11.0
53
+ aiorwlock==1.3.0
54
+ aiosignal==1.3.1
55
+ aiosqlite==0.19.0
56
+ albumentations==1.4.0
57
+ alembic==1.13.1
58
+ altair==5.3.0
59
+ annotated-types==0.6.0
60
+ annoy==1.17.3
61
+ anyio==4.2.0
62
+ apache-beam==2.46.0
63
+ aplus==0.11.0
64
+ appdirs==1.4.4
65
+ archspec==0.2.3
66
+ argon2-cffi-bindings==21.2.0
67
+ argon2-cffi==23.1.0
68
+ array-record==0.5.0
69
+ arrow==1.3.0
70
+ arviz==0.17.1
71
+ astroid==3.1.0
72
+ astropy-iers-data==0.2024.4.1.0.33.14
73
+ astropy==6.0.1
74
+ asttokens==2.4.1
75
+ astunparse==1.6.3
76
+ async-lru==2.0.4
77
+ async-timeout==4.0.3
78
+ attrs==23.2.0
79
+ audioread==3.0.1
80
+ autopep8==2.0.4
81
+ backoff==2.2.1
82
+ bayesian-optimization==1.4.3
83
+ beatrix_jupyterlab==2023.128.151533
84
+ beautifulsoup4==4.12.2
85
+ bitsandbytes==0.43.0
86
+ blake3==0.2.1
87
+ bleach==6.1.0
88
+ blessed==1.20.0
89
+ blinker==1.7.0
90
+ blis==0.7.10
91
+ blosc2==2.6.0
92
+ bokeh==3.3.4
93
+ boltons==23.1.1
94
+ boto3==1.26.100
95
+ botocore==1.34.51
96
+ bq_helper==0.4.1
97
+ bqplot==0.12.43
98
+ branca==0.7.1
99
+ brewer2mpl==1.4.1
100
+ brotlipy==0.7.0
101
+ cached-property==1.5.2
102
+ cachetools==4.2.4
103
+ cachetools==5.3.2
104
+ catalogue==2.0.10
105
+ catalyst==22.4
106
+ catboost==1.2.3
107
+ category-encoders==2.6.3
108
+ certifi==2024.2.2
109
+ cesium==0.12.1
110
+ cffi==1.16.0
111
+ charset-normalizer==3.3.2
112
+ chex==0.1.86
113
+ cleverhans==4.0.0
114
+ click-plugins==1.1.1
115
+ click==8.1.7
116
+ cligj==0.7.2
117
+ cloud-tpu-client==0.10
118
+ cloud-tpu-profiler==2.4.0
119
+ cloudpathlib==0.16.0
120
+ cloudpickle==2.2.1
121
+ cloudpickle==3.0.0
122
+ cmdstanpy==1.2.2
123
+ colorama==0.4.6
124
+ colorcet==3.1.0
125
+ colorful==0.5.6
126
+ colorlog==6.8.2
127
+ colorlover==0.3.0
128
+ comm==0.2.1
129
+ conda-libmamba-solver==23.7.0
130
+ conda-package-handling==2.2.0
131
+ conda==23.7.4
132
+ conda_package_streaming==0.9.0
133
+ confection==0.1.4
134
+ contextily==1.6.0
135
+ contourpy==1.2.0
136
+ convertdate==2.4.0
137
+ crcmod==1.7
138
+ cryptography==41.0.7
139
+ cuda-python==12.4.0
140
+ cudf==23.8.0
141
+ cufflinks==0.17.3
142
+ cuml==23.8.0
143
+ cupy==13.0.0
144
+ cycler==0.12.1
145
+ cymem==2.0.8
146
+ cytoolz==0.12.3
147
+ daal4py==2024.2.0
148
+ daal==2024.2.0
149
+ dacite==1.8.1
150
+ dask-cuda==23.8.0
151
+ dask-cudf==23.8.0
152
+ dask-expr==1.0.9
153
+ dask==2024.4.0
154
+ dataclasses-json==0.6.4
155
+ dataproc_jupyter_plugin==0.1.66
156
+ datasets==2.16.0
157
+ datashader==0.16.0
158
+ datatile==1.0.3
159
+ db-dtypes==1.2.0
160
+ deap==1.4.1
161
+ debugpy==1.8.0
162
+ decorator==5.1.1
163
+ deepdiff==6.7.1
164
+ defusedxml==0.7.1
165
+ deprecation==2.1.0
166
+ descartes==1.1.0
167
+ dill==0.3.7
168
+ dipy==1.9.0
169
+ distlib==0.3.8
170
+ distributed==2023.7.1
171
+ distro==1.9.0
172
+ dm-tree==0.1.8
173
+ docker-pycreds==0.4.0
174
+ docker==7.0.0
175
+ docopt==0.6.2
176
+ docstring-parser==0.15
177
+ docstring-to-markdown==0.15
178
+ docutils==0.20.1
179
+ earthengine-api==0.1.395
180
+ easydict==1.13
181
+ easyocr==1.7.1
182
+ ecos==2.0.13
183
+ eli5==0.13.0
184
+ emoji==2.11.0
185
+ en-core-web-lg==3.7.1
186
+ en-core-web-sm==3.7.1
187
+ entrypoints==0.4
188
+ ephem==4.1.5
189
+ esda==2.5.1
190
+ essentia==2.1b6.dev1110
191
+ et-xmlfile==1.1.0
192
+ etils==1.6.0
193
+ exceptiongroup==1.2.0
194
+ executing==2.0.1
195
+ explainable-ai-sdk==1.3.3
196
+ fastai==2.7.14
197
+ fastapi==0.108.0
198
+ fastavro==1.9.3
199
+ fastcore==1.5.29
200
+ fastdownload==0.0.7
201
+ fasteners==0.19
202
+ fastjsonschema==2.19.1
203
+ fastprogress==1.0.3
204
+ fastrlock==0.8.2
205
+ fasttext==0.9.2
206
+ feather-format==0.4.1
207
+ featuretools==1.30.0
208
+ filelock==3.13.1
209
+ fiona==1.9.6
210
+ fitter==1.7.0
211
+ flake8==7.0.0
212
+ flashtext==2.7
213
+ flatbuffers==23.5.26
214
+ flax==0.8.2
215
+ folium==0.16.0
216
+ fonttools==4.47.0
217
+ fonttools==4.50.0
218
+ fqdn==1.5.1
219
+ frozendict==2.4.1
220
+ frozenlist==1.4.1
221
+ fsspec==2023.10.0
222
+ fsspec==2024.3.1
223
+ funcy==2.0
224
+ fury==0.10.0
225
+ future==1.0.0
226
+ fuzzywuzzy==0.18.0
227
+ gast==0.5.4
228
+ gatspy==0.3
229
+ gcsfs==2024.2.0
230
+ gensim==4.3.2
231
+ geographiclib==2.0
232
+ geojson==3.1.0
233
+ geopandas==0.14.3
234
+ geoplot==0.5.1
235
+ geopy==2.4.1
236
+ geoviews==1.11.1
237
+ ggplot==0.11.5
238
+ giddy==2.3.5
239
+ gitdb==4.0.11
240
+ google-ai-generativelanguage==0.4.0
241
+ google-api-core==2.11.1
242
+ google-api-core==2.18.0
243
+ google-api-python-client==2.125.0
244
+ google-apitools==0.5.31
245
+ google-auth-httplib2==0.2.0
246
+ google-auth-oauthlib==1.2.0
247
+ google-auth==2.26.1
248
+ google-cloud-aiplatform==0.6.0a1
249
+ google-cloud-artifact-registry==1.10.0
250
+ google-cloud-automl==1.0.1
251
+ google-cloud-bigquery==2.34.4
252
+ google-cloud-bigtable==1.7.3
253
+ google-cloud-core==2.4.1
254
+ google-cloud-datastore==2.19.0
255
+ google-cloud-dlp==3.14.0
256
+ google-cloud-jupyter-config==0.0.5
257
+ google-cloud-language==2.13.3
258
+ google-cloud-monitoring==2.18.0
259
+ google-cloud-pubsub==2.19.0
260
+ google-cloud-pubsublite==1.9.0
261
+ google-cloud-recommendations-ai==0.7.1
262
+ google-cloud-resource-manager==1.11.0
263
+ google-cloud-spanner==3.40.1
264
+ google-cloud-storage==1.44.0
265
+ google-cloud-translate==3.12.1
266
+ google-cloud-videointelligence==2.13.3
267
+ google-cloud-vision==2.8.0
268
+ google-crc32c==1.5.0
269
+ google-generativeai==0.4.1
270
+ google-pasta==0.2.0
271
+ google-resumable-media==2.7.0
272
+ googleapis-common-protos==1.62.0
273
+ gplearn==0.4.2
274
+ gpustat==1.0.0
275
+ gpxpy==1.6.2
276
+ graphviz==0.20.3
277
+ greenlet==3.0.3
278
+ grpc-google-iam-v1==0.12.7
279
+ grpcio-status==1.48.1
280
+ grpcio-status==1.48.2
281
+ grpcio==1.51.1
282
+ grpcio==1.60.0
283
+ gviz-api==1.10.0
284
+ gym-notices==0.0.8
285
+ gym==0.26.2
286
+ gymnasium==0.29.0
287
+ h11==0.14.0
288
+ h2o==3.46.0.1
289
+ h5netcdf==1.3.0
290
+ h5py==3.10.0
291
+ haversine==2.8.1
292
+ hdfs==2.7.3
293
+ hep-ml==0.7.2
294
+ hijri-converter==2.3.1
295
+ hmmlearn==0.3.2
296
+ holidays==0.24
297
+ holoviews==1.18.3
298
+ hpsklearn==0.1.0
299
+ html5lib==1.1
300
+ htmlmin==0.1.12
301
+ httpcore==1.0.5
302
+ httplib2==0.21.0
303
+ httptools==0.6.1
304
+ httpx==0.27.0
305
+ huggingface-hub==0.22.2
306
+ hunspell==0.5.5
307
+ hydra-slayer==0.5.0
308
+ hyperopt==0.2.7
309
+ hypertools==0.8.0
310
+ idna==3.6
311
+ igraph==0.11.4
312
+ imagecodecs==2024.1.1
313
+ imageio==2.33.1
314
+ imbalanced-learn==0.12.2
315
+ imgaug==0.4.0
316
+ importlib-metadata==6.11.0
317
+ importlib-metadata==7.0.1
318
+ importlib-resources==6.1.1
319
+ inequality==1.0.1
320
+ iniconfig==2.0.0
321
+ ipydatawidgets==4.3.5
322
+ ipykernel==6.28.0
323
+ ipyleaflet==0.18.2
324
+ ipympl==0.7.0
325
+ ipython-genutils==0.2.0
326
+ ipython-genutils==0.2.0
327
+ ipython-sql==0.5.0
328
+ ipython==8.20.0
329
+ ipyvolume==0.6.3
330
+ ipyvue==1.10.2
331
+ ipyvuetify==1.9.3
332
+ ipywebrtc==0.6.0
333
+ ipywidgets==7.7.1
334
+ isoduration==20.11.0
335
+ isort==5.13.2
336
+ isoweek==1.3.3
337
+ itsdangerous==2.1.2
338
+ jaraco.classes==3.3.0
339
+ jax-jumpy==1.0.0
340
+ jax==0.4.23
341
+ jaxlib==0.4.23.dev20240116
342
+ jedi==0.19.1
343
+ jeepney==0.8.0
344
+ jieba==0.42.1
345
+ jmespath==1.0.1
346
+ joblib==1.3.2
347
+ json5==0.9.14
348
+ jsonpatch==1.33
349
+ jsonpointer==2.4
350
+ jsonschema-specifications==2023.12.1
351
+ jsonschema==4.20.0
352
+ jupyter-console==6.6.3
353
+ jupyter-events==0.9.0
354
+ jupyter-http-over-ws==0.0.8
355
+ jupyter-lsp==1.5.1
356
+ jupyter-server-mathjax==0.2.6
357
+ jupyter-ydoc==0.2.5
358
+ jupyter_client==7.4.9
359
+ jupyter_client==8.6.0
360
+ jupyter_core==5.7.1
361
+ jupyter_server==2.13.0
362
+ jupyter_server_fileid==0.9.1
363
+ jupyter_server_proxy==4.1.0
364
+ jupyter_server_terminals==0.5.1
365
+ jupyter_server_ydoc==0.8.0
366
+ jupyterlab-lsp==5.1.0
367
+ jupyterlab-widgets==3.0.9
368
+ jupyterlab==4.1.5
369
+ jupyterlab_git==0.44.0
370
+ jupyterlab_pygments==0.3.0
371
+ jupyterlab_server==2.25.2
372
+ jupytext==1.16.0
373
+ kaggle-environments==1.14.3
374
+ kaggle==1.6.8
375
+ kagglehub==0.2.2
376
+ keras-cv==0.8.2
377
+ keras-nlp==0.8.2
378
+ keras-tuner==1.4.6
379
+ keras==3.1.1
380
+ kernels-mixer==0.0.7
381
+ keyring==24.3.0
382
+ keyrings.google-artifactregistry-auth==1.1.2
383
+ kfp-pipeline-spec==0.2.2
384
+ kfp-server-api==2.0.5
385
+ kfp==2.5.0
386
+ kiwisolver==1.4.5
387
+ kmapper==2.0.1
388
+ kmodes==0.12.2
389
+ korean-lunar-calendar==0.3.1
390
+ kornia==0.7.2
391
+ kornia_rs==0.1.3
392
+ kt-legacy==1.0.5
393
+ kubernetes==26.1.0
394
+ langcodes==3.3.0
395
+ langid==1.1.6
396
+ lazy_loader==0.3
397
+ learntools==0.3.4
398
+ leven==1.0.4
399
+ libclang==16.0.6
400
+ libmambapy==1.5.0
401
+ libpysal==4.9.2
402
+ librosa==0.10.1
403
+ lightgbm==4.2.0
404
+ lightning-utilities==0.11.2
405
+ lime==0.2.0.1
406
+ line-profiler==4.1.2
407
+ linkify-it-py==2.0.3
408
+ llvmlite==0.41.1
409
+ llvmlite==0.42.0
410
+ lml==0.1.0
411
+ locket==1.0.0
412
+ loguru==0.7.2
413
+ lxml==5.2.1
414
+ lz4==4.3.3
415
+ mamba==1.5.0
416
+ mapclassify==2.6.1
417
+ markdown-it-py==3.0.0
418
+ marshmallow==3.21.1
419
+ matplotlib-inline==0.1.6
420
+ matplotlib-venn==0.11.10
421
+ matplotlib==3.7.5
422
+ matplotlib==3.8.3
423
+ mccabe==0.7.0
424
+ mdit-py-plugins==0.4.0
425
+ mdurl==0.1.2
426
+ memory-profiler==0.61.0
427
+ menuinst==2.0.1
428
+ mercantile==1.2.1
429
+ mgwr==2.2.1
430
+ missingno==0.5.2
431
+ mistune==0.8.4
432
+ mizani==0.11.1
433
+ ml-dtypes==0.2.0
434
+ mlcrate==0.2.0
435
+ mlens==0.2.3
436
+ mlxtend==0.23.1
437
+ mne==1.6.1
438
+ mnist==0.2.2
439
+ momepy==0.7.0
440
+ more-itertools==10.2.0
441
+ mpld3==0.5.10
442
+ mpmath==1.3.0
443
+ msgpack==1.0.7
444
+ multidict==6.0.4
445
+ multimethod==1.10
446
+ multipledispatch==1.0.0
447
+ multiprocess==0.70.15
448
+ munkres==1.1.4
449
+ murmurhash==1.0.10
450
+ mypy-extensions==1.0.0
451
+ namex==0.0.7
452
+ nb-conda-kernels==2.3.1
453
+ nb_conda==2.2.1
454
+ nbclassic==1.0.0
455
+ nbclient==0.5.13
456
+ nbconvert==6.4.5
457
+ nbdime==3.2.0
458
+ nbformat==5.9.2
459
+ ndindex==1.8
460
+ nest-asyncio==1.5.8
461
+ networkx==3.2.1
462
+ nibabel==5.2.1
463
+ nilearn==0.10.3
464
+ ninja==1.11.1.1
465
+ nltk==3.2.4
466
+ nose==1.3.7
467
+ notebook==6.5.4
468
+ notebook==6.5.6
469
+ notebook_executor==0.2
470
+ notebook_shim==0.2.3
471
+ numba==0.58.1
472
+ numba==0.59.1
473
+ numexpr==2.10.0
474
+ numpy==1.26.4
475
+ nvidia-ml-py==11.495.46
476
+ nvtx==0.2.10
477
+ oauth2client==4.1.3
478
+ oauthlib==3.2.2
479
+ objsize==0.6.1
480
+ odfpy==1.4.1
481
+ olefile==0.47
482
+ onnx==1.16.0
483
+ opencensus-context==0.1.3
484
+ opencensus==0.11.4
485
+ opencv-contrib-python==4.9.0.80
486
+ opencv-python-headless==4.9.0.80
487
+ opencv-python==4.9.0.80
488
+ openpyxl==3.1.2
489
+ openslide-python==1.3.1
490
+ opentelemetry-api==1.22.0
491
+ opentelemetry-exporter-otlp-proto-common==1.22.0
492
+ opentelemetry-exporter-otlp-proto-grpc==1.22.0
493
+ opentelemetry-exporter-otlp-proto-http==1.22.0
494
+ opentelemetry-exporter-otlp==1.22.0
495
+ opentelemetry-proto==1.22.0
496
+ opentelemetry-sdk==1.22.0
497
+ opentelemetry-semantic-conventions==0.43b0
498
+ opt-einsum==3.3.0
499
+ optax==0.2.2
500
+ optree==0.11.0
501
+ optuna==3.6.1
502
+ orbax-checkpoint==0.5.7
503
+ ordered-set==4.1.0
504
+ orjson==3.9.10
505
+ ortools==9.4.1874
506
+ osmnx==1.9.2
507
+ overrides==7.4.0
508
+ packaging==21.3
509
+ pandas-datareader==0.10.0
510
+ pandas-profiling==3.6.6
511
+ pandas-summary==0.2.0
512
+ pandas==2.1.4
513
+ pandas==2.2.1
514
+ pandasql==0.7.3
515
+ pandocfilters==1.5.0
516
+ panel==1.3.8
517
+ papermill==2.5.0
518
+ param==2.1.0
519
+ parso==0.8.3
520
+ partd==1.4.1
521
+ path.py==12.5.0
522
+ path==16.10.0
523
+ pathos==0.3.2
524
+ pathy==0.10.3
525
+ patsy==0.5.6
526
+ pdf2image==1.17.0
527
+ peft==0.10.0
528
+ pettingzoo==1.24.0
529
+ pexpect==4.8.0
530
+ pexpect==4.9.0
531
+ phik==0.12.4
532
+ pickleshare==0.7.5
533
+ pillow==10.3.0
534
+ pip==23.3.2
535
+ pkgutil_resolve_name==1.3.10
536
+ platformdirs==4.2.0
537
+ plotly-express==0.4.1
538
+ plotly==5.18.0
539
+ plotnine==0.13.4
540
+ pluggy==1.4.0
541
+ pointpats==2.4.0
542
+ polars==0.20.18
543
+ polyglot==16.7.4
544
+ pooch==1.8.1
545
+ pox==0.3.4
546
+ ppca==0.0.4
547
+ ppft==1.7.6.8
548
+ preprocessing==0.1.13
549
+ preshed==3.0.9
550
+ prettytable==3.9.0
551
+ progressbar2==4.4.2
552
+ prometheus-client==0.19.0
553
+ promise==2.3
554
+ prompt-toolkit==3.0.42
555
+ prompt-toolkit==3.0.43
556
+ prophet==1.1.1
557
+ proto-plus==1.23.0
558
+ protobuf==3.20.3
559
+ protobuf==4.21.12
560
+ psutil==5.9.3
561
+ psutil==5.9.7
562
+ ptyprocess==0.7.0
563
+ pudb==2024.1
564
+ pure-eval==0.2.2
565
+ py-cpuinfo==9.0.0
566
+ py-spy==0.3.14
567
+ py4j==0.10.9.7
568
+ pyLDAvis==3.4.1
569
+ pyOpenSSL==23.3.0
570
+ pyaml==23.12.0
571
+ pyarrow-hotfix==0.6
572
+ pyarrow==15.0.2
573
+ pyasn1-modules==0.3.0
574
+ pyasn1==0.5.1
575
+ pybind11==2.12.0
576
+ pyclipper==1.3.0.post5
577
+ pycodestyle==2.11.1
578
+ pycosat==0.6.6
579
+ pycparser==2.21
580
+ pycryptodome==3.20.0
581
+ pyct==0.5.0
582
+ pycuda==2024.1
583
+ pydantic==2.5.3
584
+ pydantic==2.6.4
585
+ pydantic_core==2.14.6
586
+ pydantic_core==2.16.3
587
+ pydegensac==0.1.2
588
+ pydicom==2.4.4
589
+ pydocstyle==6.3.0
590
+ pydot==1.4.2
591
+ pydub==0.25.1
592
+ pyemd==1.0.0
593
+ pyerfa==2.0.1.1
594
+ pyexcel-io==0.6.6
595
+ pyexcel-ods==0.6.0
596
+ pyflakes==3.2.0
597
+ pygltflib==1.16.2
598
+ pykalman==0.9.7
599
+ pylibraft==23.8.0
600
+ pylint==3.1.0
601
+ pymc3==3.11.4
602
+ pymongo==3.13.0
603
+ pynndescent==0.5.12
604
+ pynvml==11.4.1
605
+ pynvrtc==9.2
606
+ pyparsing==3.1.1
607
+ pyparsing==3.1.2
608
+ pypdf==4.1.0
609
+ pyproj==3.6.1
610
+ pysal==24.1
611
+ pyshp==2.3.1
612
+ pytesseract==0.3.10
613
+ pytest==8.1.1
614
+ python-bidi==0.4.2
615
+ python-dateutil==2.9.0.post0
616
+ python-dotenv==1.0.0
617
+ python-json-logger==2.0.7
618
+ python-louvain==0.16
619
+ python-lsp-jsonrpc==1.1.2
620
+ python-lsp-server==1.11.0
621
+ python-slugify==8.0.4
622
+ python-utils==3.8.2
623
+ pythreejs==2.4.2
624
+ pytoolconfig==1.3.1
625
+ pytools==2024.1.1
626
+ pytorch-ignite==0.5.0.post2
627
+ pytorch-lightning==2.2.1
628
+ pytz==2023.3.post1
629
+ pytz==2024.1
630
+ pyu2f==0.1.5
631
+ pyviz_comms==3.0.2
632
+ pyzmq==24.0.1
633
+ pyzmq==25.1.2
634
+ qgrid==1.3.1
635
+ qtconsole==5.5.1
636
+ quantecon==0.7.2
637
+ qudida==0.0.4
638
+ raft-dask==23.8.0
639
+ rasterio==1.3.9
640
+ rasterstats==0.19.0
641
+ ray-cpp==2.9.0
642
+ ray==2.9.0
643
+ referencing==0.32.1
644
+ regex==2023.12.25
645
+ requests-oauthlib==1.3.1
646
+ requests-toolbelt==0.10.1
647
+ requests==2.31.0
648
+ retrying==1.3.3
649
+ retrying==1.3.4
650
+ rfc3339-validator==0.1.4
651
+ rfc3986-validator==0.1.1
652
+ rgf-python==3.12.0
653
+ rich-click==1.7.4
654
+ rich==13.7.0
655
+ rich==13.7.1
656
+ rmm==23.8.0
657
+ rope==1.13.0
658
+ rpds-py==0.16.2
659
+ rsa==4.9
660
+ ruamel-yaml-conda==0.15.100
661
+ ruamel.yaml.clib==0.2.7
662
+ ruamel.yaml==0.17.40
663
+ s2sphere==0.2.5
664
+ s3fs==2024.2.0
665
+ s3transfer==0.6.2
666
+ safetensors==0.4.2
667
+ scattertext==0.1.19
668
+ scikit-image==0.22.0
669
+ scikit-learn-intelex==2024.2.0
670
+ scikit-learn==1.2.2
671
+ scikit-multilearn==0.2.0
672
+ scikit-optimize==0.10.1
673
+ scikit-plot==0.3.7
674
+ scikit-surprise==1.1.3
675
+ scipy==1.11.4
676
+ scipy==1.12.0
677
+ seaborn==0.12.2
678
+ segment_anything==1.0
679
+ segregation==2.5
680
+ semver==3.0.2
681
+ sentencepiece==0.2.0
682
+ sentry-sdk==1.44.1
683
+ setproctitle==1.3.3
684
+ setuptools-git==1.2
685
+ setuptools-scm==8.0.4
686
+ setuptools==69.0.3
687
+ shap==0.44.1
688
+ shapely==2.0.3
689
+ shellingham==1.5.4
690
+ shtab==1.7.1
691
+ simpervisor==1.0.0
692
+ simplejson==3.19.2
693
+ six==1.16.0
694
+ sklearn-pandas==2.2.0
695
+ slicer==0.0.7
696
+ smart-open==6.4.0
697
+ smmap==5.0.1
698
+ sniffio==1.3.0
699
+ snowballstemmer==2.2.0
700
+ snuggs==1.4.7
701
+ sortedcontainers==2.4.0
702
+ soundfile==0.12.1
703
+ soupsieve==2.5
704
+ soxr==0.3.7
705
+ spacy-legacy==3.0.12
706
+ spacy-loggers==1.0.5
707
+ spacy==3.7.2
708
+ spaghetti==1.7.5.post1
709
+ spectral==0.23.1
710
+ spglm==1.1.0
711
+ sphinx-rtd-theme==0.2.4
712
+ spint==1.0.7
713
+ splot==1.1.5.post1
714
+ spopt==0.6.0
715
+ spreg==1.4.2
716
+ spvcm==0.3.0
717
+ sqlparse==0.4.4
718
+ squarify==0.4.3
719
+ srsly==2.4.8
720
+ stable-baselines3==2.1.0
721
+ stack-data==0.6.2
722
+ stack-data==0.6.3
723
+ stanio==0.5.0
724
+ starlette==0.32.0.post1
725
+ statsmodels==0.14.1
726
+ stemming==1.0.1
727
+ stop-words==2018.7.23
728
+ stopit==1.1.2
729
+ stumpy==1.12.0
730
+ sympy==1.12
731
+ tables==3.9.2
732
+ tabulate==0.9.0
733
+ tangled-up-in-unicode==0.2.0
734
+ tbb==2021.12.0
735
+ tblib==3.0.0
736
+ tenacity==8.2.3
737
+ tensorboard-data-server==0.7.2
738
+ tensorboard-plugin-profile==2.15.0
739
+ tensorboard==2.15.1
740
+ tensorboardX==2.6.2.2
741
+ tensorflow-cloud==0.1.16
742
+ tensorflow-datasets==4.9.4
743
+ tensorflow-decision-forests==1.8.1
744
+ tensorflow-estimator==2.15.0
745
+ tensorflow-hub==0.16.1
746
+ tensorflow-io-gcs-filesystem==0.35.0
747
+ tensorflow-io==0.35.0
748
+ tensorflow-metadata==0.14.0
749
+ tensorflow-probability==0.23.0
750
+ tensorflow-serving-api==2.14.1
751
+ tensorflow-text==2.15.0
752
+ tensorflow-transform==0.14.0
753
+ tensorflow==2.15.0
754
+ tensorstore==0.1.56
755
+ termcolor==2.4.0
756
+ terminado==0.18.0
757
+ testpath==0.6.0
758
+ text-unidecode==1.3
759
+ textblob==0.18.0.post0
760
+ texttable==1.7.0
761
+ tf_keras==2.15.1
762
+ tfp-nightly==0.24.0.dev0
763
+ thinc==8.2.2
764
+ threadpoolctl==3.2.0
765
+ tifffile==2023.12.9
766
+ timm==0.9.16
767
+ tinycss2==1.2.1
768
+ tobler==0.11.2
769
+ tokenizers==0.15.2
770
+ toml==0.10.2
771
+ tomli==2.0.1
772
+ tomlkit==0.12.4
773
+ toolz==0.12.1
774
+ torch==2.1.2
775
+ torchaudio==2.1.2
776
+ torchdata==0.7.1
777
+ torchinfo==1.8.0
778
+ torchmetrics==1.3.2
779
+ torchtext==0.16.2
780
+ torchvision==0.16.2
781
+ tornado==6.3.3
782
+ tqdm==4.66.1
783
+ traceml==1.0.8
784
+ traitlets==5.9.0
785
+ traittypes==0.2.1
786
+ transformers==4.39.3
787
+ treelite-runtime==3.2.0
788
+ treelite==3.2.0
789
+ trl==0.8.1
790
+ truststore==0.8.0
791
+ trx-python==0.2.9
792
+ tsfresh==0.20.2
793
+ typeguard==4.1.5
794
+ typer==0.9.0
795
+ typer==0.9.4
796
+ types-python-dateutil==2.8.19.20240106
797
+ typing-inspect==0.9.0
798
+ typing-utils==0.1.0
799
+ typing_extensions==4.9.0
800
+ tyro==0.8.3
801
+ tzdata==2023.4
802
+ uc-micro-py==1.0.3
803
+ ucx-py==0.33.0
804
+ ujson==5.9.0
805
+ umap-learn==0.5.5
806
+ unicodedata2==15.1.0
807
+ update-checker==0.18.0
808
+ uri-template==1.3.0
809
+ uritemplate==3.0.1
810
+ urllib3==1.26.18
811
+ urllib3==2.1.0
812
+ urwid==2.6.10
813
+ urwid_readline==0.14
814
+ uvicorn==0.25.0
815
+ uvloop==0.19.0
816
+ vaex-astro==0.9.3
817
+ vaex-core==4.17.1
818
+ vaex-hdf5==0.14.1
819
+ vaex-jupyter==0.8.2
820
+ vaex-ml==0.18.3
821
+ vaex-server==0.9.0
822
+ vaex-viz==0.5.4
823
+ vaex==4.17.0
824
+ vec_noise==1.1.4
825
+ vecstack==0.4.0
826
+ virtualenv==20.21.0
827
+ visions==0.7.5
828
+ vowpalwabbit==9.9.0
829
+ vtk==9.3.0
830
+ wandb==0.16.5
831
+ wasabi==1.1.2
832
+ watchfiles==0.21.0
833
+ wavio==0.0.8
834
+ wcwidth==0.2.13
835
+ weasel==0.3.4
836
+ webcolors==1.13
837
+ webencodings==0.5.1
838
+ websocket-client==1.7.0
839
+ websockets==12.0
840
+ wfdb==4.1.2
841
+ whatthepatch==1.0.5
842
+ wheel==0.42.0
843
+ widgetsnbextension==3.6.6
844
+ witwidget==1.8.1
845
+ woodwork==0.29.0
846
+ wordcloud==1.9.3
847
+ wordsegment==1.3.1
848
+ wrapt==1.14.1
849
+ xarray-einstats==0.7.0
850
+ xarray==2024.3.0
851
+ xgboost==2.0.3
852
+ xvfbwrapper==0.2.9
853
+ xxhash==3.4.1
854
+ xyzservices==2023.10.1
855
+ y-py==0.6.2
856
+ yapf==0.40.2
857
+ yarl==1.9.3
858
+ yarl==1.9.4
859
+ ydata-profiling==4.6.4
860
+ yellowbrick==1.5
861
+ ypy-websocket==0.8.4
862
+ zict==3.0.0
863
+ zipp==3.17.0
864
+ zstandard==0.22.0
wandb/run-20240411_035909-21esl9hl/files/wandb-metadata.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.15.133+-x86_64-with-glibc2.31",
3
+ "python": "3.10.13",
4
+ "heartbeatAt": "2024-04-11T03:59:10.650560",
5
+ "startedAt": "2024-04-11T03:59:09.933024",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [],
9
+ "state": "running",
10
+ "program": "kaggle.ipynb",
11
+ "codePathLocal": null,
12
+ "root": "/kaggle/working",
13
+ "host": "321ddc84c049",
14
+ "username": "root",
15
+ "executable": "/opt/conda/bin/python3.10",
16
+ "cpu_count": 2,
17
+ "cpu_count_logical": 4,
18
+ "cpu_freq": {
19
+ "current": 2000.19,
20
+ "min": 0.0,
21
+ "max": 0.0
22
+ },
23
+ "cpu_freq_per_core": [
24
+ {
25
+ "current": 2000.19,
26
+ "min": 0.0,
27
+ "max": 0.0
28
+ },
29
+ {
30
+ "current": 2000.19,
31
+ "min": 0.0,
32
+ "max": 0.0
33
+ },
34
+ {
35
+ "current": 2000.19,
36
+ "min": 0.0,
37
+ "max": 0.0
38
+ },
39
+ {
40
+ "current": 2000.19,
41
+ "min": 0.0,
42
+ "max": 0.0
43
+ }
44
+ ],
45
+ "disk": {
46
+ "/": {
47
+ "total": 8062.387607574463,
48
+ "used": 5566.961940765381
49
+ }
50
+ },
51
+ "gpu": "Tesla T4",
52
+ "gpu_count": 2,
53
+ "gpu_devices": [
54
+ {
55
+ "name": "Tesla T4",
56
+ "memory_total": 16106127360
57
+ },
58
+ {
59
+ "name": "Tesla T4",
60
+ "memory_total": 16106127360
61
+ }
62
+ ],
63
+ "memory": {
64
+ "total": 31.357559204101562
65
+ }
66
+ }
wandb/run-20240411_035909-21esl9hl/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train_runtime": 14.0567, "train_samples_per_second": 2.846, "train_steps_per_second": 0.711, "total_flos": 28907911741440.0, "train_loss": 21.220675659179687, "train/epoch": 0.0, "train/global_step": 10, "_timestamp": 1712808008.9437401, "_runtime": 59.003005027770996, "_step": 0}
wandb/run-20240411_035909-21esl9hl/logs/debug-internal.log ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-04-11 03:59:09,940 INFO StreamThr :191 [internal.py:wandb_internal():86] W&B internal server running at pid: 191, started at: 2024-04-11 03:59:09.939664
2
+ 2024-04-11 03:59:09,941 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status
3
+ 2024-04-11 03:59:10,363 INFO WriterThread:191 [datastore.py:open_for_write():87] open: /kaggle/working/wandb/run-20240411_035909-21esl9hl/run-21esl9hl.wandb
4
+ 2024-04-11 03:59:10,364 DEBUG SenderThread:191 [sender.py:send():379] send: header
5
+ 2024-04-11 03:59:10,367 DEBUG SenderThread:191 [sender.py:send():379] send: run
6
+ 2024-04-11 03:59:10,517 INFO SenderThread:191 [dir_watcher.py:__init__():211] watching files in: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files
7
+ 2024-04-11 03:59:10,517 INFO SenderThread:191 [sender.py:_start_run_threads():1124] run started: 21esl9hl with start time 1712807949.940735
8
+ 2024-04-11 03:59:10,526 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: check_version
9
+ 2024-04-11 03:59:10,526 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: check_version
10
+ 2024-04-11 03:59:10,621 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: run_start
11
+ 2024-04-11 03:59:10,635 DEBUG HandlerThread:191 [system_info.py:__init__():26] System info init
12
+ 2024-04-11 03:59:10,635 DEBUG HandlerThread:191 [system_info.py:__init__():41] System info init done
13
+ 2024-04-11 03:59:10,635 INFO HandlerThread:191 [system_monitor.py:start():194] Starting system monitor
14
+ 2024-04-11 03:59:10,635 INFO SystemMonitor:191 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
+ 2024-04-11 03:59:10,635 INFO HandlerThread:191 [system_monitor.py:probe():214] Collecting system info
16
+ 2024-04-11 03:59:10,639 INFO SystemMonitor:191 [interfaces.py:start():190] Started cpu monitoring
17
+ 2024-04-11 03:59:10,640 INFO SystemMonitor:191 [interfaces.py:start():190] Started disk monitoring
18
+ 2024-04-11 03:59:10,644 INFO SystemMonitor:191 [interfaces.py:start():190] Started gpu monitoring
19
+ 2024-04-11 03:59:10,644 INFO SystemMonitor:191 [interfaces.py:start():190] Started memory monitoring
20
+ 2024-04-11 03:59:10,645 INFO SystemMonitor:191 [interfaces.py:start():190] Started network monitoring
21
+ 2024-04-11 03:59:10,650 DEBUG HandlerThread:191 [system_info.py:probe():150] Probing system
22
+ 2024-04-11 03:59:10,652 DEBUG HandlerThread:191 [gitlib.py:_init_repo():56] git repository is invalid
23
+ 2024-04-11 03:59:10,652 DEBUG HandlerThread:191 [system_info.py:probe():198] Probing system done
24
+ 2024-04-11 03:59:10,652 DEBUG HandlerThread:191 [system_monitor.py:probe():223] {'os': 'Linux-5.15.133+-x86_64-with-glibc2.31', 'python': '3.10.13', 'heartbeatAt': '2024-04-11T03:59:10.650560', 'startedAt': '2024-04-11T03:59:09.933024', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'kaggle.ipynb', 'codePathLocal': None, 'root': '/kaggle/working', 'host': '321ddc84c049', 'username': 'root', 'executable': '/opt/conda/bin/python3.10', 'cpu_count': 2, 'cpu_count_logical': 4, 'cpu_freq': {'current': 2000.19, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2000.19, 'min': 0.0, 'max': 0.0}, {'current': 2000.19, 'min': 0.0, 'max': 0.0}, {'current': 2000.19, 'min': 0.0, 'max': 0.0}, {'current': 2000.19, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 8062.387607574463, 'used': 5566.961940765381}}, 'gpu': 'Tesla T4', 'gpu_count': 2, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}, {'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 31.357559204101562}}
25
+ 2024-04-11 03:59:10,653 INFO HandlerThread:191 [system_monitor.py:probe():224] Finished collecting system info
26
+ 2024-04-11 03:59:10,653 INFO HandlerThread:191 [system_monitor.py:probe():227] Publishing system info
27
+ 2024-04-11 03:59:10,653 DEBUG HandlerThread:191 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
28
+ 2024-04-11 03:59:11,520 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/conda-environment.yaml
29
+ 2024-04-11 03:59:25,667 ERROR HandlerThread:191 [system_info.py:_save_conda():221] Error saving conda packages: Command '['conda', 'env', 'export']' timed out after 15 seconds
30
+ Traceback (most recent call last):
31
+ File "/opt/conda/lib/python3.10/site-packages/wandb/sdk/internal/system/system_info.py", line 214, in _save_conda
32
+ subprocess.call(
33
+ File "/opt/conda/lib/python3.10/subprocess.py", line 347, in call
34
+ return p.wait(timeout=timeout)
35
+ File "/opt/conda/lib/python3.10/subprocess.py", line 1209, in wait
36
+ return self._wait(timeout=timeout)
37
+ File "/opt/conda/lib/python3.10/subprocess.py", line 1951, in _wait
38
+ raise TimeoutExpired(self.args, timeout)
39
+ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after 15 seconds
40
+ 2024-04-11 03:59:25,670 DEBUG HandlerThread:191 [system_info.py:_save_conda():222] Saving conda packages done
41
+ 2024-04-11 03:59:25,671 INFO HandlerThread:191 [system_monitor.py:probe():229] Finished publishing system info
42
+ 2024-04-11 03:59:25,678 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
43
+ 2024-04-11 03:59:25,678 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: keepalive
44
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
45
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: keepalive
46
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
47
+ 2024-04-11 03:59:25,679 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: keepalive
48
+ 2024-04-11 03:59:25,679 DEBUG SenderThread:191 [sender.py:send():379] send: files
49
+ 2024-04-11 03:59:25,680 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
50
+ 2024-04-11 03:59:25,883 INFO wandb-upload_0:191 [upload_job.py:push():131] Uploaded file /tmp/tmpgmb8demxwandb/zh9coxtl-wandb-metadata.json
51
+ 2024-04-11 03:59:26,522 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/wandb-metadata.json
52
+ 2024-04-11 03:59:26,714 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: python_packages
53
+ 2024-04-11 03:59:26,714 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: python_packages
54
+ 2024-04-11 03:59:26,717 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
55
+ 2024-04-11 03:59:26,727 DEBUG SenderThread:191 [sender.py:send():379] send: config
56
+ 2024-04-11 03:59:26,728 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
57
+ 2024-04-11 03:59:26,729 DEBUG SenderThread:191 [sender.py:send():379] send: metric
58
+ 2024-04-11 03:59:26,729 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
59
+ 2024-04-11 03:59:26,730 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
60
+ 2024-04-11 03:59:26,731 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
61
+ 2024-04-11 03:59:26,776 DEBUG SenderThread:191 [sender.py:send():379] send: metric
62
+ 2024-04-11 03:59:26,776 WARNING SenderThread:191 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
63
+ 2024-04-11 03:59:26,776 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
64
+ 2024-04-11 03:59:27,522 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/requirements.txt
65
+ 2024-04-11 03:59:27,523 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
66
+ 2024-04-11 03:59:29,523 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
67
+ 2024-04-11 03:59:30,951 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
68
+ 2024-04-11 03:59:31,524 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
69
+ 2024-04-11 03:59:33,525 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
70
+ 2024-04-11 03:59:35,952 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
71
+ 2024-04-11 03:59:40,958 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
72
+ 2024-04-11 03:59:41,528 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/config.yaml
73
+ 2024-04-11 03:59:41,717 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
74
+ 2024-04-11 03:59:41,717 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
75
+ 2024-04-11 03:59:41,718 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
76
+ 2024-04-11 03:59:45,530 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
77
+ 2024-04-11 03:59:46,261 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
78
+ 2024-04-11 03:59:51,262 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
79
+ 2024-04-11 03:59:56,417 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
80
+ 2024-04-11 03:59:56,717 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
81
+ 2024-04-11 03:59:56,718 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
82
+ 2024-04-11 03:59:56,719 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
83
+ 2024-04-11 03:59:57,534 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
84
+ 2024-04-11 04:00:01,827 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
85
+ 2024-04-11 04:00:06,828 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
86
+ 2024-04-11 04:00:08,943 DEBUG SenderThread:191 [sender.py:send():379] send: telemetry
87
+ 2024-04-11 04:00:08,983 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: partial_history
88
+ 2024-04-11 04:00:08,985 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
89
+ 2024-04-11 04:00:08,988 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
90
+ 2024-04-11 04:00:08,988 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
91
+ 2024-04-11 04:00:08,989 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
92
+ 2024-04-11 04:00:08,989 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
93
+ 2024-04-11 04:00:08,989 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
94
+ 2024-04-11 04:00:08,989 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
95
+ 2024-04-11 04:00:08,990 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
96
+ 2024-04-11 04:00:08,990 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
97
+ 2024-04-11 04:00:08,990 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
98
+ 2024-04-11 04:00:08,990 DEBUG SenderThread:191 [sender.py:send():379] send: metric
99
+ 2024-04-11 04:00:08,991 DEBUG SenderThread:191 [sender.py:send():379] send: history
100
+ 2024-04-11 04:00:08,991 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: summary_record
101
+ 2024-04-11 04:00:08,991 INFO SenderThread:191 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
102
+ 2024-04-11 04:00:09,539 INFO Thread-12 :191 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/wandb-summary.json
103
+ 2024-04-11 04:00:10,645 DEBUG SystemMonitor:191 [system_monitor.py:_start():172] Starting system metrics aggregation loop
104
+ 2024-04-11 04:00:10,647 DEBUG SenderThread:191 [sender.py:send():379] send: stats
105
+ 2024-04-11 04:00:11,539 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/output.log
106
+ 2024-04-11 04:00:11,715 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
107
+ 2024-04-11 04:00:11,716 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
108
+ 2024-04-11 04:00:11,719 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
109
+ 2024-04-11 04:00:11,833 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
110
+ 2024-04-11 04:00:12,540 INFO Thread-12 :191 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240411_035909-21esl9hl/files/config.yaml
111
+ 2024-04-11 04:00:16,925 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
112
+ 2024-04-11 04:00:21,926 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
113
+ 2024-04-11 04:00:26,716 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: stop_status
114
+ 2024-04-11 04:00:26,716 DEBUG SenderThread:191 [sender.py:send_request():406] send_request: stop_status
115
+ 2024-04-11 04:00:26,757 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: internal_messages
116
+ 2024-04-11 04:00:27,786 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
117
+ 2024-04-11 04:00:32,787 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
118
+ 2024-04-11 04:00:37,788 DEBUG HandlerThread:191 [handler.py:handle_request():146] handle_request: status_report
wandb/run-20240411_035909-21esl9hl/logs/debug.log ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-04-11 03:59:09,934 INFO MainThread:145 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
2
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Configure stats pid to 145
3
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
5
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Applying login settings: {}
9
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
10
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240411_035909-21esl9hl/logs/debug.log
11
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240411_035909-21esl9hl/logs/debug-internal.log
12
+ 2024-04-11 03:59:09,935 INFO MainThread:145 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7e1d3f588970>
13
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():567] calling init triggers
14
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
15
+ config: {}
16
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():617] starting backend
17
+ 2024-04-11 03:59:09,936 INFO MainThread:145 [wandb_init.py:init():621] setting up manager
18
+ 2024-04-11 03:59:09,938 INFO MainThread:145 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
19
+ 2024-04-11 03:59:09,940 INFO MainThread:145 [wandb_init.py:init():629] backend started and connected
20
+ 2024-04-11 03:59:09,953 INFO MainThread:145 [wandb_run.py:_label_probe_notebook():1299] probe notebook
21
+ 2024-04-11 03:59:10,362 INFO MainThread:145 [wandb_init.py:init():721] updated telemetry
22
+ 2024-04-11 03:59:10,366 INFO MainThread:145 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
23
+ 2024-04-11 03:59:10,526 INFO MainThread:145 [wandb_run.py:_on_init():2344] communicating current version
24
+ 2024-04-11 03:59:10,613 INFO MainThread:145 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
25
+
26
+ 2024-04-11 03:59:10,614 INFO MainThread:145 [wandb_init.py:init():805] starting run threads in backend
27
+ 2024-04-11 03:59:26,715 INFO MainThread:145 [wandb_run.py:_console_start():2323] atexit reg
28
+ 2024-04-11 03:59:26,715 INFO MainThread:145 [wandb_run.py:_redirect():2178] redirect: wrap_raw
29
+ 2024-04-11 03:59:26,716 INFO MainThread:145 [wandb_run.py:_redirect():2243] Wrapping output streams.
30
+ 2024-04-11 03:59:26,716 INFO MainThread:145 [wandb_run.py:_redirect():2268] Redirects installed.
31
+ 2024-04-11 03:59:26,717 INFO MainThread:145 [wandb_init.py:init():848] run started, returning control to user process
32
+ 2024-04-11 03:59:26,723 INFO MainThread:145 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1024, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-560m', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': False, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 10, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr11_03-48-59_321ddc84c049', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 8, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': True, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
wandb/run-20240411_035909-21esl9hl/run-21esl9hl.wandb ADDED
Binary file (18.5 kB). View file