csujeong commited on
Commit
0157bf9
1 Parent(s): 4dd897e

Training in progress, step 10

Browse files
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "tiiuae/falcon-7b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "dense",
23
+ "dense_h_to_4h",
24
+ "dense_4h_to_h",
25
+ "query_key_value"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e52f2f5d7543e51fee5b18fb7053085e7aec3d80525ac3a73ed7837c7e3acc
3
+ size 261131840
runs/Dec23_12-50-32_e914d23c8e31/events.out.tfevents.1703335862.e914d23c8e31.1666.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8749c6e12f8414cf3d64e81940bd28fc2e8d141753a311ba5e0bb3811418e0
3
+ size 5645
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "<|endoftext|>"
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ }
100
+ },
101
+ "additional_special_tokens": [
102
+ ">>TITLE<<",
103
+ ">>ABSTRACT<<",
104
+ ">>INTRODUCTION<<",
105
+ ">>SUMMARY<<",
106
+ ">>COMMENT<<",
107
+ ">>ANSWER<<",
108
+ ">>QUESTION<<",
109
+ ">>DOMAIN<<",
110
+ ">>PREFIX<<",
111
+ ">>SUFFIX<<",
112
+ ">>MIDDLE<<"
113
+ ],
114
+ "clean_up_tokenization_spaces": true,
115
+ "eos_token": "<|endoftext|>",
116
+ "model_input_names": [
117
+ "input_ids",
118
+ "attention_mask"
119
+ ],
120
+ "model_max_length": 2048,
121
+ "pad_token": "<|endoftext|>",
122
+ "tokenizer_class": "PreTrainedTokenizerFast"
123
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c4f7103959a2239ab6fb7cf81b44f6b0f17f2bca5ae15adffeefb17833a422
3
+ size 4792
wandb/debug-internal.log ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-12-23 12:52:09,951 INFO StreamThr :4184 [internal.py:wandb_internal():86] W&B internal server running at pid: 4184, started at: 2023-12-23 12:52:09.937331
2
+ 2023-12-23 12:52:09,956 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status
3
+ 2023-12-23 12:52:11,771 INFO WriterThread:4184 [datastore.py:open_for_write():85] open: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/run-wzwtpkqz.wandb
4
+ 2023-12-23 12:52:11,774 DEBUG SenderThread:4184 [sender.py:send():382] send: header
5
+ 2023-12-23 12:52:11,783 DEBUG SenderThread:4184 [sender.py:send():382] send: run
6
+ 2023-12-23 12:52:12,213 INFO SenderThread:4184 [dir_watcher.py:__init__():211] watching files in: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files
7
+ 2023-12-23 12:52:12,213 INFO SenderThread:4184 [sender.py:_start_run_threads():1136] run started: wzwtpkqz with start time 1703335929.930536
8
+ 2023-12-23 12:52:12,224 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: check_version
9
+ 2023-12-23 12:52:12,225 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: check_version
10
+ 2023-12-23 12:52:12,369 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: run_start
11
+ 2023-12-23 12:52:12,379 DEBUG HandlerThread:4184 [system_info.py:__init__():32] System info init
12
+ 2023-12-23 12:52:12,379 DEBUG HandlerThread:4184 [system_info.py:__init__():47] System info init done
13
+ 2023-12-23 12:52:12,380 INFO HandlerThread:4184 [system_monitor.py:start():194] Starting system monitor
14
+ 2023-12-23 12:52:12,380 INFO SystemMonitor:4184 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
+ 2023-12-23 12:52:12,380 INFO HandlerThread:4184 [system_monitor.py:probe():214] Collecting system info
16
+ 2023-12-23 12:52:12,381 INFO SystemMonitor:4184 [interfaces.py:start():190] Started cpu monitoring
17
+ 2023-12-23 12:52:12,382 INFO SystemMonitor:4184 [interfaces.py:start():190] Started disk monitoring
18
+ 2023-12-23 12:52:12,385 INFO SystemMonitor:4184 [interfaces.py:start():190] Started gpu monitoring
19
+ 2023-12-23 12:52:12,386 INFO SystemMonitor:4184 [interfaces.py:start():190] Started memory monitoring
20
+ 2023-12-23 12:52:12,386 INFO SystemMonitor:4184 [interfaces.py:start():190] Started network monitoring
21
+ 2023-12-23 12:52:12,389 DEBUG HandlerThread:4184 [system_info.py:probe():196] Probing system
22
+ 2023-12-23 12:52:12,394 DEBUG HandlerThread:4184 [gitlib.py:_init_repo():56] git repository is invalid
23
+ 2023-12-23 12:52:12,394 DEBUG HandlerThread:4184 [system_info.py:probe():244] Probing system done
24
+ 2023-12-23 12:52:12,394 DEBUG HandlerThread:4184 [system_monitor.py:probe():223] {'os': 'Linux-6.1.58+-x86_64-with-glibc2.35', 'python': '3.10.12', 'heartbeatAt': '2023-12-23T12:52:12.389569', 'startedAt': '2023-12-23T12:52:09.884051', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'falcon_financial_finetuning.ipynb', 'codePathLocal': None, 'colab': 'https://colab.research.google.com/notebook#fileId=1Wrk8K8X1p4XNKtZeX4rFgUqxQB3WPL1M', 'host': 'e914d23c8e31', 'username': 'root', 'executable': '/usr/bin/python3', 'cpu_count': 1, 'cpu_count_logical': 2, '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}], 'disk': {'/': {'total': 78.1898422241211, 'used': 40.1796989440918}}, 'gpu': 'Tesla T4', 'gpu_count': 1, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 12.674781799316406}}
25
+ 2023-12-23 12:52:12,394 INFO HandlerThread:4184 [system_monitor.py:probe():224] Finished collecting system info
26
+ 2023-12-23 12:52:12,395 INFO HandlerThread:4184 [system_monitor.py:probe():227] Publishing system info
27
+ 2023-12-23 12:52:12,395 DEBUG HandlerThread:4184 [system_info.py:_save_pip():52] Saving list of pip packages installed into the current environment
28
+ 2023-12-23 12:52:12,399 DEBUG HandlerThread:4184 [system_info.py:_save_pip():68] Saving pip packages done
29
+ 2023-12-23 12:52:12,403 INFO HandlerThread:4184 [system_monitor.py:probe():229] Finished publishing system info
30
+ 2023-12-23 12:52:12,429 DEBUG SenderThread:4184 [sender.py:send():382] send: files
31
+ 2023-12-23 12:52:12,429 INFO SenderThread:4184 [sender.py:_save_file():1392] saving file wandb-metadata.json with policy now
32
+ 2023-12-23 12:52:12,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
33
+ 2023-12-23 12:52:12,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
34
+ 2023-12-23 12:52:12,456 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
35
+ 2023-12-23 12:52:12,673 DEBUG SenderThread:4184 [sender.py:send():382] send: telemetry
36
+ 2023-12-23 12:52:12,674 DEBUG SenderThread:4184 [sender.py:send():382] send: config
37
+ 2023-12-23 12:52:12,675 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
38
+ 2023-12-23 12:52:12,676 DEBUG SenderThread:4184 [sender.py:send():382] send: telemetry
39
+ 2023-12-23 12:52:12,676 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
40
+ 2023-12-23 12:52:12,676 WARNING SenderThread:4184 [sender.py:send_metric():1343] Seen metric with glob (shouldn't happen)
41
+ 2023-12-23 12:52:12,676 DEBUG SenderThread:4184 [sender.py:send():382] send: telemetry
42
+ 2023-12-23 12:52:12,955 INFO wandb-upload_0:4184 [upload_job.py:push():131] Uploaded file /tmp/tmpk8by8xfswandb/i7g1zhkv-wandb-metadata.json
43
+ 2023-12-23 12:52:13,218 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/wandb-metadata.json
44
+ 2023-12-23 12:52:13,218 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/requirements.txt
45
+ 2023-12-23 12:52:13,219 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/output.log
46
+ 2023-12-23 12:52:15,680 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
47
+ 2023-12-23 12:52:20,681 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
48
+ 2023-12-23 12:52:25,682 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
49
+ 2023-12-23 12:52:27,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
50
+ 2023-12-23 12:52:27,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
51
+ 2023-12-23 12:52:27,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
52
+ 2023-12-23 12:52:31,606 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
53
+ 2023-12-23 12:52:36,606 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
54
+ 2023-12-23 12:52:41,614 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
55
+ 2023-12-23 12:52:42,269 INFO Thread-12 :4184 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/config.yaml
56
+ 2023-12-23 12:52:42,456 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
57
+ 2023-12-23 12:52:42,456 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
58
+ 2023-12-23 12:52:42,457 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
59
+ 2023-12-23 12:52:47,544 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
60
+ 2023-12-23 12:52:52,545 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
61
+ 2023-12-23 12:52:57,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
62
+ 2023-12-23 12:52:57,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
63
+ 2023-12-23 12:52:57,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
64
+ 2023-12-23 12:52:57,584 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
65
+ 2023-12-23 12:53:02,584 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
66
+ 2023-12-23 12:53:07,585 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
67
+ 2023-12-23 12:53:12,387 DEBUG SystemMonitor:4184 [system_monitor.py:_start():172] Starting system metrics aggregation loop
68
+ 2023-12-23 12:53:12,388 DEBUG SenderThread:4184 [sender.py:send():382] send: stats
69
+ 2023-12-23 12:53:12,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
70
+ 2023-12-23 12:53:12,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
71
+ 2023-12-23 12:53:12,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
72
+ 2023-12-23 12:53:12,620 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
73
+ 2023-12-23 12:53:17,621 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
74
+ 2023-12-23 12:53:22,622 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
75
+ 2023-12-23 12:53:27,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
76
+ 2023-12-23 12:53:27,456 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
77
+ 2023-12-23 12:53:27,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
78
+ 2023-12-23 12:53:27,625 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
79
+ 2023-12-23 12:53:32,626 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
80
+ 2023-12-23 12:53:37,626 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
81
+ 2023-12-23 12:53:42,389 DEBUG SenderThread:4184 [sender.py:send():382] send: stats
82
+ 2023-12-23 12:53:42,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
83
+ 2023-12-23 12:53:42,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
84
+ 2023-12-23 12:53:42,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
85
+ 2023-12-23 12:53:43,569 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
86
+ 2023-12-23 12:53:45,806 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: partial_history
87
+ 2023-12-23 12:53:45,809 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
88
+ 2023-12-23 12:53:45,809 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
89
+ 2023-12-23 12:53:45,810 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
90
+ 2023-12-23 12:53:45,810 DEBUG SenderThread:4184 [sender.py:send():382] send: history
91
+ 2023-12-23 12:53:45,810 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: summary_record
92
+ 2023-12-23 12:53:45,814 INFO SenderThread:4184 [sender.py:_save_file():1392] saving file wandb-summary.json with policy end
93
+ 2023-12-23 12:53:46,399 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/wandb-summary.json
94
+ 2023-12-23 12:53:48,816 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
95
+ 2023-12-23 12:53:53,817 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
96
+ 2023-12-23 12:53:54,502 INFO Thread-12 :4184 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/output.log
97
+ 2023-12-23 12:53:57,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
98
+ 2023-12-23 12:53:57,456 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
99
+ 2023-12-23 12:53:57,457 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
100
+ 2023-12-23 12:53:59,685 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
101
+ 2023-12-23 12:54:04,686 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
wandb/debug.log ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-12-23 12:52:09,917 INFO MainThread:1666 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
2
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Configure stats pid to 1666
3
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Loading settings from /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/settings
5
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
9
+ 2023-12-23 12:52:09,919 INFO MainThread:1666 [wandb_init.py:_log_setup():524] Logging user logs to /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/logs/debug.log
10
+ 2023-12-23 12:52:09,919 INFO MainThread:1666 [wandb_init.py:_log_setup():525] Logging internal logs to /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/logs/debug-internal.log
11
+ 2023-12-23 12:52:09,920 INFO MainThread:1666 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7ce3202b90f0>
12
+ 2023-12-23 12:52:09,920 INFO MainThread:1666 [wandb_init.py:init():564] calling init triggers
13
+ 2023-12-23 12:52:09,921 INFO MainThread:1666 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
14
+ config: {}
15
+ 2023-12-23 12:52:09,921 INFO MainThread:1666 [wandb_init.py:init():614] starting backend
16
+ 2023-12-23 12:52:09,921 INFO MainThread:1666 [wandb_init.py:init():618] setting up manager
17
+ 2023-12-23 12:52:09,928 INFO MainThread:1666 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2023-12-23 12:52:09,930 INFO MainThread:1666 [wandb_init.py:init():624] backend started and connected
19
+ 2023-12-23 12:52:09,979 INFO MainThread:1666 [wandb_run.py:_label_probe_notebook():1294] probe notebook
20
+ 2023-12-23 12:52:11,770 INFO MainThread:1666 [wandb_init.py:init():716] updated telemetry
21
+ 2023-12-23 12:52:11,782 INFO MainThread:1666 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
22
+ 2023-12-23 12:52:12,224 INFO MainThread:1666 [wandb_run.py:_on_init():2254] communicating current version
23
+ 2023-12-23 12:52:12,358 INFO MainThread:1666 [wandb_run.py:_on_init():2263] got version response
24
+ 2023-12-23 12:52:12,359 INFO MainThread:1666 [wandb_init.py:init():800] starting run threads in backend
25
+ 2023-12-23 12:52:12,454 INFO MainThread:1666 [wandb_run.py:_console_start():2233] atexit reg
26
+ 2023-12-23 12:52:12,455 INFO MainThread:1666 [wandb_run.py:_redirect():2088] redirect: wrap_raw
27
+ 2023-12-23 12:52:12,455 INFO MainThread:1666 [wandb_run.py:_redirect():2153] Wrapping output streams.
28
+ 2023-12-23 12:52:12,455 INFO MainThread:1666 [wandb_run.py:_redirect():2178] Redirects installed.
29
+ 2023-12-23 12:52:12,457 INFO MainThread:1666 [wandb_init.py:init():841] run started, returning control to user process
30
+ 2023-12-23 12:52:12,466 INFO MainThread:1666 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 65024, 'hidden_size': 4544, 'num_hidden_layers': 32, 'num_attention_heads': 71, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 11, 'eos_token_id': 11, 'num_kv_heads': 71, 'alibi': False, 'new_decoder_architecture': False, 'multi_query': True, 'parallel_attn': True, 'bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, '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, 'chunk_size_feed_forward': 0, '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': ['FalconForCausalLM'], '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': None, 'problem_type': None, '_name_or_path': 'tiiuae/falcon-7b', 'transformers_version': '4.36.2', 'apply_residual_connection_post_layernorm': False, 'auto_map': {'AutoConfig': 'tiiuae/falcon-7b--configuration_falcon.FalconConfig', 'AutoModel': 'tiiuae/falcon-7b--modeling_falcon.FalconModel', 'AutoModelForSequenceClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification', 'AutoModelForTokenClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification', 'AutoModelForQuestionAnswering': 'tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering', 'AutoModelForCausalLM': 'tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM'}, 'model_type': 'falcon', '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': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial', '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': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 80, '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': '/content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/runs/Dec23_12-50-32_e914d23c8e31', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, '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': False, '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': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, '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': True, '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': False, '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': False, '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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
wandb/run-20231223_125209-wzwtpkqz/files/config.yaml ADDED
@@ -0,0 +1,660 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.10.12
7
+ cli_version: 0.16.1
8
+ framework: huggingface
9
+ huggingface_version: 4.36.2
10
+ is_jupyter_run: true
11
+ is_kaggle_kernel: false
12
+ start_time: 1703335929.930536
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
+ 2:
29
+ - 1
30
+ - 2
31
+ - 3
32
+ - 5
33
+ - 11
34
+ - 12
35
+ - 49
36
+ - 51
37
+ - 53
38
+ - 55
39
+ - 71
40
+ - 84
41
+ - 98
42
+ 3:
43
+ - 7
44
+ - 23
45
+ 4: 3.10.12
46
+ 5: 0.16.1
47
+ 6: 4.36.2
48
+ 8:
49
+ - 1
50
+ - 5
51
+ - 12
52
+ 9:
53
+ 1: transformers_trainer
54
+ 13: linux-x86_64
55
+ m:
56
+ - 1: train/global_step
57
+ 6:
58
+ - 3
59
+ vocab_size:
60
+ desc: null
61
+ value: 65024
62
+ hidden_size:
63
+ desc: null
64
+ value: 4544
65
+ num_hidden_layers:
66
+ desc: null
67
+ value: 32
68
+ num_attention_heads:
69
+ desc: null
70
+ value: 71
71
+ layer_norm_epsilon:
72
+ desc: null
73
+ value: 1.0e-05
74
+ initializer_range:
75
+ desc: null
76
+ value: 0.02
77
+ use_cache:
78
+ desc: null
79
+ value: false
80
+ hidden_dropout:
81
+ desc: null
82
+ value: 0.0
83
+ attention_dropout:
84
+ desc: null
85
+ value: 0.0
86
+ bos_token_id:
87
+ desc: null
88
+ value: 11
89
+ eos_token_id:
90
+ desc: null
91
+ value: 11
92
+ num_kv_heads:
93
+ desc: null
94
+ value: 71
95
+ alibi:
96
+ desc: null
97
+ value: false
98
+ new_decoder_architecture:
99
+ desc: null
100
+ value: false
101
+ multi_query:
102
+ desc: null
103
+ value: true
104
+ parallel_attn:
105
+ desc: null
106
+ value: true
107
+ bias:
108
+ desc: null
109
+ value: false
110
+ return_dict:
111
+ desc: null
112
+ value: true
113
+ output_hidden_states:
114
+ desc: null
115
+ value: false
116
+ output_attentions:
117
+ desc: null
118
+ value: false
119
+ torchscript:
120
+ desc: null
121
+ value: false
122
+ torch_dtype:
123
+ desc: null
124
+ value: bfloat16
125
+ use_bfloat16:
126
+ desc: null
127
+ value: false
128
+ tf_legacy_loss:
129
+ desc: null
130
+ value: false
131
+ pruned_heads:
132
+ desc: null
133
+ value: {}
134
+ tie_word_embeddings:
135
+ desc: null
136
+ value: true
137
+ is_encoder_decoder:
138
+ desc: null
139
+ value: false
140
+ is_decoder:
141
+ desc: null
142
+ value: false
143
+ cross_attention_hidden_size:
144
+ desc: null
145
+ value: null
146
+ add_cross_attention:
147
+ desc: null
148
+ value: false
149
+ tie_encoder_decoder:
150
+ desc: null
151
+ value: false
152
+ max_length:
153
+ desc: null
154
+ value: 20
155
+ min_length:
156
+ desc: null
157
+ value: 0
158
+ do_sample:
159
+ desc: null
160
+ value: false
161
+ early_stopping:
162
+ desc: null
163
+ value: false
164
+ num_beams:
165
+ desc: null
166
+ value: 1
167
+ num_beam_groups:
168
+ desc: null
169
+ value: 1
170
+ diversity_penalty:
171
+ desc: null
172
+ value: 0.0
173
+ temperature:
174
+ desc: null
175
+ value: 1.0
176
+ top_k:
177
+ desc: null
178
+ value: 50
179
+ top_p:
180
+ desc: null
181
+ value: 1.0
182
+ typical_p:
183
+ desc: null
184
+ value: 1.0
185
+ repetition_penalty:
186
+ desc: null
187
+ value: 1.0
188
+ length_penalty:
189
+ desc: null
190
+ value: 1.0
191
+ no_repeat_ngram_size:
192
+ desc: null
193
+ value: 0
194
+ encoder_no_repeat_ngram_size:
195
+ desc: null
196
+ value: 0
197
+ bad_words_ids:
198
+ desc: null
199
+ value: null
200
+ num_return_sequences:
201
+ desc: null
202
+ value: 1
203
+ chunk_size_feed_forward:
204
+ desc: null
205
+ value: 0
206
+ output_scores:
207
+ desc: null
208
+ value: false
209
+ return_dict_in_generate:
210
+ desc: null
211
+ value: false
212
+ forced_bos_token_id:
213
+ desc: null
214
+ value: null
215
+ forced_eos_token_id:
216
+ desc: null
217
+ value: null
218
+ remove_invalid_values:
219
+ desc: null
220
+ value: false
221
+ exponential_decay_length_penalty:
222
+ desc: null
223
+ value: null
224
+ suppress_tokens:
225
+ desc: null
226
+ value: null
227
+ begin_suppress_tokens:
228
+ desc: null
229
+ value: null
230
+ architectures:
231
+ desc: null
232
+ value:
233
+ - FalconForCausalLM
234
+ finetuning_task:
235
+ desc: null
236
+ value: null
237
+ id2label:
238
+ desc: null
239
+ value:
240
+ '0': LABEL_0
241
+ '1': LABEL_1
242
+ label2id:
243
+ desc: null
244
+ value:
245
+ LABEL_0: 0
246
+ LABEL_1: 1
247
+ tokenizer_class:
248
+ desc: null
249
+ value: null
250
+ prefix:
251
+ desc: null
252
+ value: null
253
+ pad_token_id:
254
+ desc: null
255
+ value: null
256
+ sep_token_id:
257
+ desc: null
258
+ value: null
259
+ decoder_start_token_id:
260
+ desc: null
261
+ value: null
262
+ task_specific_params:
263
+ desc: null
264
+ value: null
265
+ problem_type:
266
+ desc: null
267
+ value: null
268
+ _name_or_path:
269
+ desc: null
270
+ value: tiiuae/falcon-7b
271
+ transformers_version:
272
+ desc: null
273
+ value: 4.36.2
274
+ apply_residual_connection_post_layernorm:
275
+ desc: null
276
+ value: false
277
+ auto_map:
278
+ desc: null
279
+ value:
280
+ AutoConfig: tiiuae/falcon-7b--configuration_falcon.FalconConfig
281
+ AutoModel: tiiuae/falcon-7b--modeling_falcon.FalconModel
282
+ AutoModelForSequenceClassification: tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification
283
+ AutoModelForTokenClassification: tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification
284
+ AutoModelForQuestionAnswering: tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering
285
+ AutoModelForCausalLM: tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM
286
+ model_type:
287
+ desc: null
288
+ value: falcon
289
+ quantization_config:
290
+ desc: null
291
+ value:
292
+ quant_method: QuantizationMethod.BITS_AND_BYTES
293
+ load_in_8bit: false
294
+ load_in_4bit: true
295
+ llm_int8_threshold: 6.0
296
+ llm_int8_skip_modules: null
297
+ llm_int8_enable_fp32_cpu_offload: false
298
+ llm_int8_has_fp16_weight: false
299
+ bnb_4bit_quant_type: nf4
300
+ bnb_4bit_use_double_quant: true
301
+ bnb_4bit_compute_dtype: bfloat16
302
+ output_dir:
303
+ desc: null
304
+ value: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial
305
+ overwrite_output_dir:
306
+ desc: null
307
+ value: false
308
+ do_train:
309
+ desc: null
310
+ value: false
311
+ do_eval:
312
+ desc: null
313
+ value: false
314
+ do_predict:
315
+ desc: null
316
+ value: false
317
+ evaluation_strategy:
318
+ desc: null
319
+ value: 'no'
320
+ prediction_loss_only:
321
+ desc: null
322
+ value: false
323
+ per_device_train_batch_size:
324
+ desc: null
325
+ value: 2
326
+ per_device_eval_batch_size:
327
+ desc: null
328
+ value: 8
329
+ per_gpu_train_batch_size:
330
+ desc: null
331
+ value: null
332
+ per_gpu_eval_batch_size:
333
+ desc: null
334
+ value: null
335
+ gradient_accumulation_steps:
336
+ desc: null
337
+ value: 2
338
+ eval_accumulation_steps:
339
+ desc: null
340
+ value: null
341
+ eval_delay:
342
+ desc: null
343
+ value: 0
344
+ learning_rate:
345
+ desc: null
346
+ value: 0.0002
347
+ weight_decay:
348
+ desc: null
349
+ value: 0.0
350
+ adam_beta1:
351
+ desc: null
352
+ value: 0.9
353
+ adam_beta2:
354
+ desc: null
355
+ value: 0.999
356
+ adam_epsilon:
357
+ desc: null
358
+ value: 1.0e-08
359
+ max_grad_norm:
360
+ desc: null
361
+ value: 0.3
362
+ num_train_epochs:
363
+ desc: null
364
+ value: 3.0
365
+ max_steps:
366
+ desc: null
367
+ value: 80
368
+ lr_scheduler_type:
369
+ desc: null
370
+ value: cosine
371
+ lr_scheduler_kwargs:
372
+ desc: null
373
+ value: {}
374
+ warmup_ratio:
375
+ desc: null
376
+ value: 0.03
377
+ warmup_steps:
378
+ desc: null
379
+ value: 0
380
+ log_level:
381
+ desc: null
382
+ value: passive
383
+ log_level_replica:
384
+ desc: null
385
+ value: warning
386
+ log_on_each_node:
387
+ desc: null
388
+ value: true
389
+ logging_dir:
390
+ desc: null
391
+ value: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/runs/Dec23_12-50-32_e914d23c8e31
392
+ logging_strategy:
393
+ desc: null
394
+ value: steps
395
+ logging_first_step:
396
+ desc: null
397
+ value: false
398
+ logging_steps:
399
+ desc: null
400
+ value: 10
401
+ logging_nan_inf_filter:
402
+ desc: null
403
+ value: true
404
+ save_strategy:
405
+ desc: null
406
+ value: steps
407
+ save_steps:
408
+ desc: null
409
+ value: 10
410
+ save_total_limit:
411
+ desc: null
412
+ value: null
413
+ save_safetensors:
414
+ desc: null
415
+ value: true
416
+ save_on_each_node:
417
+ desc: null
418
+ value: false
419
+ save_only_model:
420
+ desc: null
421
+ value: false
422
+ no_cuda:
423
+ desc: null
424
+ value: false
425
+ use_cpu:
426
+ desc: null
427
+ value: false
428
+ use_mps_device:
429
+ desc: null
430
+ value: false
431
+ seed:
432
+ desc: null
433
+ value: 42
434
+ data_seed:
435
+ desc: null
436
+ value: null
437
+ jit_mode_eval:
438
+ desc: null
439
+ value: false
440
+ use_ipex:
441
+ desc: null
442
+ value: false
443
+ bf16:
444
+ desc: null
445
+ value: false
446
+ fp16:
447
+ desc: null
448
+ value: false
449
+ fp16_opt_level:
450
+ desc: null
451
+ value: O1
452
+ half_precision_backend:
453
+ desc: null
454
+ value: auto
455
+ bf16_full_eval:
456
+ desc: null
457
+ value: false
458
+ fp16_full_eval:
459
+ desc: null
460
+ value: false
461
+ tf32:
462
+ desc: null
463
+ value: false
464
+ local_rank:
465
+ desc: null
466
+ value: 0
467
+ ddp_backend:
468
+ desc: null
469
+ value: null
470
+ tpu_num_cores:
471
+ desc: null
472
+ value: null
473
+ tpu_metrics_debug:
474
+ desc: null
475
+ value: false
476
+ debug:
477
+ desc: null
478
+ value: []
479
+ dataloader_drop_last:
480
+ desc: null
481
+ value: false
482
+ eval_steps:
483
+ desc: null
484
+ value: null
485
+ dataloader_num_workers:
486
+ desc: null
487
+ value: 0
488
+ past_index:
489
+ desc: null
490
+ value: -1
491
+ run_name:
492
+ desc: null
493
+ value: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial
494
+ disable_tqdm:
495
+ desc: null
496
+ value: false
497
+ remove_unused_columns:
498
+ desc: null
499
+ value: true
500
+ label_names:
501
+ desc: null
502
+ value: null
503
+ load_best_model_at_end:
504
+ desc: null
505
+ value: false
506
+ metric_for_best_model:
507
+ desc: null
508
+ value: null
509
+ greater_is_better:
510
+ desc: null
511
+ value: null
512
+ ignore_data_skip:
513
+ desc: null
514
+ value: false
515
+ fsdp:
516
+ desc: null
517
+ value: []
518
+ fsdp_min_num_params:
519
+ desc: null
520
+ value: 0
521
+ fsdp_config:
522
+ desc: null
523
+ value:
524
+ min_num_params: 0
525
+ xla: false
526
+ xla_fsdp_grad_ckpt: false
527
+ fsdp_transformer_layer_cls_to_wrap:
528
+ desc: null
529
+ value: null
530
+ deepspeed:
531
+ desc: null
532
+ value: null
533
+ label_smoothing_factor:
534
+ desc: null
535
+ value: 0.0
536
+ optim:
537
+ desc: null
538
+ value: paged_adamw_32bit
539
+ optim_args:
540
+ desc: null
541
+ value: null
542
+ adafactor:
543
+ desc: null
544
+ value: false
545
+ group_by_length:
546
+ desc: null
547
+ value: true
548
+ length_column_name:
549
+ desc: null
550
+ value: length
551
+ report_to:
552
+ desc: null
553
+ value:
554
+ - tensorboard
555
+ - wandb
556
+ ddp_find_unused_parameters:
557
+ desc: null
558
+ value: null
559
+ ddp_bucket_cap_mb:
560
+ desc: null
561
+ value: null
562
+ ddp_broadcast_buffers:
563
+ desc: null
564
+ value: null
565
+ dataloader_pin_memory:
566
+ desc: null
567
+ value: true
568
+ dataloader_persistent_workers:
569
+ desc: null
570
+ value: false
571
+ skip_memory_metrics:
572
+ desc: null
573
+ value: true
574
+ use_legacy_prediction_loop:
575
+ desc: null
576
+ value: false
577
+ push_to_hub:
578
+ desc: null
579
+ value: true
580
+ resume_from_checkpoint:
581
+ desc: null
582
+ value: null
583
+ hub_model_id:
584
+ desc: null
585
+ value: null
586
+ hub_strategy:
587
+ desc: null
588
+ value: every_save
589
+ hub_token:
590
+ desc: null
591
+ value: <HUB_TOKEN>
592
+ hub_private_repo:
593
+ desc: null
594
+ value: false
595
+ hub_always_push:
596
+ desc: null
597
+ value: false
598
+ gradient_checkpointing:
599
+ desc: null
600
+ value: false
601
+ gradient_checkpointing_kwargs:
602
+ desc: null
603
+ value: null
604
+ include_inputs_for_metrics:
605
+ desc: null
606
+ value: false
607
+ fp16_backend:
608
+ desc: null
609
+ value: auto
610
+ push_to_hub_model_id:
611
+ desc: null
612
+ value: null
613
+ push_to_hub_organization:
614
+ desc: null
615
+ value: null
616
+ push_to_hub_token:
617
+ desc: null
618
+ value: <PUSH_TO_HUB_TOKEN>
619
+ mp_parameters:
620
+ desc: null
621
+ value: ''
622
+ auto_find_batch_size:
623
+ desc: null
624
+ value: false
625
+ full_determinism:
626
+ desc: null
627
+ value: false
628
+ torchdynamo:
629
+ desc: null
630
+ value: null
631
+ ray_scope:
632
+ desc: null
633
+ value: last
634
+ ddp_timeout:
635
+ desc: null
636
+ value: 1800
637
+ torch_compile:
638
+ desc: null
639
+ value: false
640
+ torch_compile_backend:
641
+ desc: null
642
+ value: null
643
+ torch_compile_mode:
644
+ desc: null
645
+ value: null
646
+ dispatch_batches:
647
+ desc: null
648
+ value: null
649
+ split_batches:
650
+ desc: null
651
+ value: false
652
+ include_tokens_per_second:
653
+ desc: null
654
+ value: false
655
+ include_num_input_tokens_seen:
656
+ desc: null
657
+ value: false
658
+ neftune_noise_alpha:
659
+ desc: null
660
+ value: null
wandb/run-20231223_125209-wzwtpkqz/files/output.log ADDED
@@ -0,0 +1 @@
 
 
1
+
wandb/run-20231223_125209-wzwtpkqz/files/requirements.txt ADDED
@@ -0,0 +1,497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==1.4.0
2
+ accelerate==0.25.0
3
+ aiohttp==3.9.1
4
+ aiosignal==1.3.1
5
+ alabaster==0.7.13
6
+ albumentations==1.3.1
7
+ altair==4.2.2
8
+ anyio==3.7.1
9
+ appdirs==1.4.4
10
+ argon2-cffi-bindings==21.2.0
11
+ argon2-cffi==23.1.0
12
+ array-record==0.5.0
13
+ arviz==0.15.1
14
+ astropy==5.3.4
15
+ astunparse==1.6.3
16
+ async-timeout==4.0.3
17
+ atpublic==4.0
18
+ attrs==23.1.0
19
+ audioread==3.0.1
20
+ autograd==1.6.2
21
+ babel==2.14.0
22
+ backcall==0.2.0
23
+ beautifulsoup4==4.11.2
24
+ bidict==0.22.1
25
+ bigframes==0.17.0
26
+ bitsandbytes==0.41.3.post2
27
+ bleach==6.1.0
28
+ blinker==1.4
29
+ blis==0.7.11
30
+ blosc2==2.0.0
31
+ bokeh==3.3.2
32
+ bqplot==0.12.42
33
+ branca==0.7.0
34
+ build==1.0.3
35
+ cachecontrol==0.13.1
36
+ cachetools==5.3.2
37
+ catalogue==2.0.10
38
+ certifi==2023.11.17
39
+ cffi==1.16.0
40
+ chardet==5.2.0
41
+ charset-normalizer==3.3.2
42
+ chex==0.1.7
43
+ click-plugins==1.1.1
44
+ click==8.1.7
45
+ cligj==0.7.2
46
+ cloudpickle==2.2.1
47
+ cmake==3.27.9
48
+ cmdstanpy==1.2.0
49
+ colorcet==3.0.1
50
+ colorlover==0.3.0
51
+ colour==0.1.5
52
+ community==1.0.0b1
53
+ confection==0.1.4
54
+ cons==0.4.6
55
+ contextlib2==21.6.0
56
+ contourpy==1.2.0
57
+ cryptography==41.0.7
58
+ cufflinks==0.17.3
59
+ cupy-cuda12x==12.2.0
60
+ cvxopt==1.3.2
61
+ cvxpy==1.3.2
62
+ cycler==0.12.1
63
+ cymem==2.0.8
64
+ cython==3.0.6
65
+ dask==2023.8.1
66
+ datascience==0.17.6
67
+ datasets==2.16.0
68
+ db-dtypes==1.2.0
69
+ dbus-python==1.2.18
70
+ debugpy==1.6.6
71
+ decorator==4.4.2
72
+ defusedxml==0.7.1
73
+ dill==0.3.7
74
+ diskcache==5.6.3
75
+ distributed==2023.8.1
76
+ distro==1.7.0
77
+ dlib==19.24.2
78
+ dm-tree==0.1.8
79
+ docker-pycreds==0.4.0
80
+ docstring-parser==0.15
81
+ docutils==0.18.1
82
+ dopamine-rl==4.0.6
83
+ duckdb==0.9.2
84
+ earthengine-api==0.1.384
85
+ easydict==1.11
86
+ ecos==2.0.12
87
+ editdistance==0.6.2
88
+ eerepr==0.0.4
89
+ einops==0.7.0
90
+ en-core-web-sm==3.6.0
91
+ entrypoints==0.4
92
+ et-xmlfile==1.1.0
93
+ etils==1.6.0
94
+ etuples==0.3.9
95
+ exceptiongroup==1.2.0
96
+ fastai==2.7.13
97
+ fastcore==1.5.29
98
+ fastdownload==0.0.7
99
+ fastjsonschema==2.19.0
100
+ fastprogress==1.0.3
101
+ fastrlock==0.8.2
102
+ filelock==3.13.1
103
+ fiona==1.9.5
104
+ firebase-admin==5.3.0
105
+ flask==2.2.5
106
+ flatbuffers==23.5.26
107
+ flax==0.7.5
108
+ folium==0.14.0
109
+ fonttools==4.46.0
110
+ frozendict==2.3.10
111
+ frozenlist==1.4.1
112
+ fsspec==2023.6.0
113
+ future==0.18.3
114
+ gast==0.5.4
115
+ gcsfs==2023.6.0
116
+ gdal==3.4.3
117
+ gdown==4.6.6
118
+ geemap==0.29.6
119
+ gensim==4.3.2
120
+ geocoder==1.38.1
121
+ geographiclib==2.0
122
+ geopandas==0.13.2
123
+ geopy==2.3.0
124
+ gin-config==0.5.0
125
+ gitdb==4.0.11
126
+ gitpython==3.1.40
127
+ glob2==0.7
128
+ google-ai-generativelanguage==0.4.0
129
+ google-api-core==2.11.1
130
+ google-api-python-client==2.84.0
131
+ google-auth-httplib2==0.1.1
132
+ google-auth-oauthlib==1.2.0
133
+ google-auth==2.17.3
134
+ google-cloud-aiplatform==1.38.1
135
+ google-cloud-bigquery-connection==1.12.1
136
+ google-cloud-bigquery-storage==2.24.0
137
+ google-cloud-bigquery==3.12.0
138
+ google-cloud-core==2.3.3
139
+ google-cloud-datastore==2.15.2
140
+ google-cloud-firestore==2.11.1
141
+ google-cloud-functions==1.13.3
142
+ google-cloud-iam==2.13.0
143
+ google-cloud-language==2.9.1
144
+ google-cloud-resource-manager==1.11.0
145
+ google-cloud-storage==2.8.0
146
+ google-cloud-translate==3.11.3
147
+ google-colab==1.0.0
148
+ google-crc32c==1.5.0
149
+ google-generativeai==0.3.1
150
+ google-pasta==0.2.0
151
+ google-resumable-media==2.7.0
152
+ google==2.0.3
153
+ googleapis-common-protos==1.62.0
154
+ googledrivedownloader==0.4
155
+ graphviz==0.20.1
156
+ greenlet==3.0.2
157
+ grpc-google-iam-v1==0.13.0
158
+ grpcio-status==1.48.2
159
+ grpcio==1.60.0
160
+ gspread-dataframe==3.3.1
161
+ gspread==3.4.2
162
+ gym-notices==0.0.8
163
+ gym==0.25.2
164
+ h5netcdf==1.3.0
165
+ h5py==3.9.0
166
+ holidays==0.38
167
+ holoviews==1.17.1
168
+ html5lib==1.1
169
+ httpimport==1.3.1
170
+ httplib2==0.22.0
171
+ huggingface-hub==0.19.4
172
+ humanize==4.7.0
173
+ hyperopt==0.2.7
174
+ ibis-framework==6.2.0
175
+ idna==3.6
176
+ imageio-ffmpeg==0.4.9
177
+ imageio==2.31.6
178
+ imagesize==1.4.1
179
+ imbalanced-learn==0.10.1
180
+ imgaug==0.4.0
181
+ importlib-metadata==7.0.0
182
+ importlib-resources==6.1.1
183
+ imutils==0.5.4
184
+ inflect==7.0.0
185
+ iniconfig==2.0.0
186
+ install==1.3.5
187
+ intel-openmp==2023.2.3
188
+ ipyevents==2.0.2
189
+ ipyfilechooser==0.6.0
190
+ ipykernel==5.5.6
191
+ ipyleaflet==0.18.1
192
+ ipython-genutils==0.2.0
193
+ ipython-sql==0.5.0
194
+ ipython==7.34.0
195
+ ipytree==0.2.2
196
+ ipywidgets==7.7.1
197
+ itsdangerous==2.1.2
198
+ jax==0.4.23
199
+ jaxlib==0.4.23+cuda12.cudnn89
200
+ jeepney==0.7.1
201
+ jieba==0.42.1
202
+ jinja2==3.1.2
203
+ joblib==1.3.2
204
+ jsonpickle==3.0.2
205
+ jsonschema-specifications==2023.11.2
206
+ jsonschema==4.19.2
207
+ jupyter-client==6.1.12
208
+ jupyter-console==6.1.0
209
+ jupyter-core==5.5.1
210
+ jupyter-server==1.24.0
211
+ jupyterlab-pygments==0.3.0
212
+ jupyterlab-widgets==3.0.9
213
+ kaggle==1.5.16
214
+ kagglehub==0.1.4
215
+ keras==2.15.0
216
+ keyring==23.5.0
217
+ kiwisolver==1.4.5
218
+ langcodes==3.3.0
219
+ launchpadlib==1.10.16
220
+ lazr.restfulclient==0.14.4
221
+ lazr.uri==1.0.6
222
+ lazy-loader==0.3
223
+ libclang==16.0.6
224
+ librosa==0.10.1
225
+ lida==0.0.10
226
+ lightgbm==4.1.0
227
+ linkify-it-py==2.0.2
228
+ llmx==0.0.15a0
229
+ llvmlite==0.41.1
230
+ locket==1.0.0
231
+ logical-unification==0.4.6
232
+ lxml==4.9.3
233
+ malloy==2023.1067
234
+ markdown-it-py==3.0.0
235
+ markdown==3.5.1
236
+ markupsafe==2.1.3
237
+ matplotlib-inline==0.1.6
238
+ matplotlib-venn==0.11.9
239
+ matplotlib==3.7.1
240
+ mdit-py-plugins==0.4.0
241
+ mdurl==0.1.2
242
+ minikanren==1.0.3
243
+ missingno==0.5.2
244
+ mistune==0.8.4
245
+ mizani==0.9.3
246
+ mkl==2023.2.0
247
+ ml-dtypes==0.2.0
248
+ mlxtend==0.22.0
249
+ more-itertools==10.1.0
250
+ moviepy==1.0.3
251
+ mpmath==1.3.0
252
+ msgpack==1.0.7
253
+ multidict==6.0.4
254
+ multipledispatch==1.0.0
255
+ multiprocess==0.70.15
256
+ multitasking==0.0.11
257
+ murmurhash==1.0.10
258
+ music21==9.1.0
259
+ natsort==8.4.0
260
+ nbclassic==1.0.0
261
+ nbclient==0.9.0
262
+ nbconvert==6.5.4
263
+ nbformat==5.9.2
264
+ nest-asyncio==1.5.8
265
+ networkx==3.2.1
266
+ nibabel==4.0.2
267
+ nltk==3.8.1
268
+ notebook-shim==0.2.3
269
+ notebook==6.5.5
270
+ numba==0.58.1
271
+ numexpr==2.8.8
272
+ numpy==1.23.5
273
+ oauth2client==4.1.3
274
+ oauthlib==3.2.2
275
+ opencv-contrib-python==4.8.0.76
276
+ opencv-python-headless==4.8.1.78
277
+ opencv-python==4.8.0.76
278
+ openpyxl==3.1.2
279
+ opt-einsum==3.3.0
280
+ optax==0.1.7
281
+ orbax-checkpoint==0.4.4
282
+ osqp==0.6.2.post8
283
+ packaging==23.2
284
+ pandas-datareader==0.10.0
285
+ pandas-gbq==0.19.2
286
+ pandas-stubs==1.5.3.230304
287
+ pandas==1.5.3
288
+ pandocfilters==1.5.0
289
+ panel==1.3.4
290
+ param==2.0.1
291
+ parso==0.8.3
292
+ parsy==2.1
293
+ partd==1.4.1
294
+ pathlib==1.0.1
295
+ pathy==0.10.3
296
+ patsy==0.5.4
297
+ peewee==3.17.0
298
+ peft==0.7.2.dev0
299
+ pexpect==4.9.0
300
+ pickleshare==0.7.5
301
+ pillow==9.4.0
302
+ pip-tools==6.13.0
303
+ pip==23.1.2
304
+ platformdirs==4.1.0
305
+ plotly==5.15.0
306
+ plotnine==0.12.4
307
+ pluggy==1.3.0
308
+ polars==0.17.3
309
+ pooch==1.8.0
310
+ portpicker==1.5.2
311
+ prefetch-generator==1.0.3
312
+ preshed==3.0.9
313
+ prettytable==3.9.0
314
+ proglog==0.1.10
315
+ progressbar2==4.2.0
316
+ prometheus-client==0.19.0
317
+ promise==2.3
318
+ prompt-toolkit==3.0.43
319
+ prophet==1.1.5
320
+ proto-plus==1.23.0
321
+ protobuf==3.20.3
322
+ psutil==5.9.5
323
+ psycopg2==2.9.9
324
+ ptyprocess==0.7.0
325
+ py-cpuinfo==9.0.0
326
+ py4j==0.10.9.7
327
+ pyarrow-hotfix==0.6
328
+ pyarrow==10.0.1
329
+ pyasn1-modules==0.3.0
330
+ pyasn1==0.5.1
331
+ pycocotools==2.0.7
332
+ pycparser==2.21
333
+ pyct==0.5.0
334
+ pydantic==1.10.13
335
+ pydata-google-auth==1.8.2
336
+ pydot-ng==2.0.0
337
+ pydot==1.4.2
338
+ pydotplus==2.0.2
339
+ pydrive2==1.6.3
340
+ pydrive==1.3.1
341
+ pyerfa==2.0.1.1
342
+ pygame==2.5.2
343
+ pygments==2.16.1
344
+ pygobject==3.42.1
345
+ pyjwt==2.3.0
346
+ pymc==5.7.2
347
+ pymystem3==0.2.0
348
+ pyopengl==3.1.7
349
+ pyopenssl==23.3.0
350
+ pyparsing==3.1.1
351
+ pyperclip==1.8.2
352
+ pyproj==3.6.1
353
+ pyproject-hooks==1.0.0
354
+ pyshp==2.3.1
355
+ pysocks==1.7.1
356
+ pytensor==2.14.2
357
+ pytest==7.4.3
358
+ python-apt==0.0.0
359
+ python-box==7.1.1
360
+ python-dateutil==2.8.2
361
+ python-louvain==0.16
362
+ python-slugify==8.0.1
363
+ python-utils==3.8.1
364
+ pytz==2023.3.post1
365
+ pyviz-comms==3.0.0
366
+ pywavelets==1.5.0
367
+ pyyaml==6.0.1
368
+ pyzmq==23.2.1
369
+ qdldl==0.1.7.post0
370
+ qudida==0.0.4
371
+ ratelim==0.1.6
372
+ referencing==0.32.0
373
+ regex==2023.6.3
374
+ requests-oauthlib==1.3.1
375
+ requests==2.31.0
376
+ requirements-parser==0.5.0
377
+ rich==13.7.0
378
+ rpds-py==0.15.2
379
+ rpy2==3.4.2
380
+ rsa==4.9
381
+ safetensors==0.4.1
382
+ scikit-image==0.19.3
383
+ scikit-learn==1.2.2
384
+ scipy==1.11.4
385
+ scooby==0.9.2
386
+ scs==3.2.4.post1
387
+ seaborn==0.12.2
388
+ secretstorage==3.3.1
389
+ send2trash==1.8.2
390
+ sentry-sdk==1.39.1
391
+ setproctitle==1.3.3
392
+ setuptools==67.7.2
393
+ shapely==2.0.2
394
+ shtab==1.6.5
395
+ six==1.16.0
396
+ sklearn-pandas==2.2.0
397
+ smart-open==6.4.0
398
+ smmap==5.0.1
399
+ sniffio==1.3.0
400
+ snowballstemmer==2.2.0
401
+ sortedcontainers==2.4.0
402
+ soundfile==0.12.1
403
+ soupsieve==2.5
404
+ soxr==0.3.7
405
+ spacy-legacy==3.0.12
406
+ spacy-loggers==1.0.5
407
+ spacy==3.6.1
408
+ sphinx==5.0.2
409
+ sphinxcontrib-applehelp==1.0.7
410
+ sphinxcontrib-devhelp==1.0.5
411
+ sphinxcontrib-htmlhelp==2.0.4
412
+ sphinxcontrib-jsmath==1.0.1
413
+ sphinxcontrib-qthelp==1.0.6
414
+ sphinxcontrib-serializinghtml==1.1.9
415
+ sqlalchemy==2.0.23
416
+ sqlglot==17.16.2
417
+ sqlparse==0.4.4
418
+ srsly==2.4.8
419
+ stanio==0.3.0
420
+ statsmodels==0.14.1
421
+ sympy==1.12
422
+ tables==3.8.0
423
+ tabulate==0.9.0
424
+ tbb==2021.11.0
425
+ tblib==3.0.0
426
+ tenacity==8.2.3
427
+ tensorboard-data-server==0.7.2
428
+ tensorboard==2.15.1
429
+ tensorflow-datasets==4.9.4
430
+ tensorflow-estimator==2.15.0
431
+ tensorflow-gcs-config==2.15.0
432
+ tensorflow-hub==0.15.0
433
+ tensorflow-io-gcs-filesystem==0.34.0
434
+ tensorflow-metadata==1.14.0
435
+ tensorflow-probability==0.22.0
436
+ tensorflow==2.15.0
437
+ tensorstore==0.1.45
438
+ termcolor==2.4.0
439
+ terminado==0.18.0
440
+ text-unidecode==1.3
441
+ textblob==0.17.1
442
+ tf-slim==1.1.0
443
+ thinc==8.1.12
444
+ threadpoolctl==3.2.0
445
+ tifffile==2023.12.9
446
+ tinycss2==1.2.1
447
+ tokenizers==0.15.0
448
+ toml==0.10.2
449
+ tomli==2.0.1
450
+ toolz==0.12.0
451
+ torch==2.1.0+cu121
452
+ torchaudio==2.1.0+cu121
453
+ torchdata==0.7.0
454
+ torchsummary==1.5.1
455
+ torchtext==0.16.0
456
+ torchvision==0.16.0+cu121
457
+ tornado==6.3.2
458
+ tqdm==4.66.1
459
+ traitlets==5.7.1
460
+ traittypes==0.2.1
461
+ transformers==4.36.2
462
+ triton==2.1.0
463
+ trl==0.7.6
464
+ tweepy==4.14.0
465
+ typer==0.9.0
466
+ types-pytz==2023.3.1.1
467
+ types-setuptools==69.0.0.0
468
+ typing-extensions==4.5.0
469
+ tyro==0.6.1
470
+ tzlocal==5.2
471
+ uc-micro-py==1.0.2
472
+ uritemplate==4.1.1
473
+ urllib3==2.0.7
474
+ vega-datasets==0.9.0
475
+ wadllib==1.3.6
476
+ wandb==0.16.1
477
+ wasabi==1.1.2
478
+ wcwidth==0.2.12
479
+ webcolors==1.13
480
+ webencodings==0.5.1
481
+ websocket-client==1.7.0
482
+ werkzeug==3.0.1
483
+ wheel==0.42.0
484
+ widgetsnbextension==3.6.6
485
+ wordcloud==1.9.3
486
+ wrapt==1.14.1
487
+ xarray-einstats==0.6.0
488
+ xarray==2023.7.0
489
+ xgboost==2.0.2
490
+ xlrd==2.0.1
491
+ xxhash==3.4.1
492
+ xyzservices==2023.10.1
493
+ yarl==1.9.4
494
+ yellowbrick==1.5
495
+ yfinance==0.2.33
496
+ zict==3.0.0
497
+ zipp==3.17.0
wandb/run-20231223_125209-wzwtpkqz/files/wandb-metadata.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.1.58+-x86_64-with-glibc2.35",
3
+ "python": "3.10.12",
4
+ "heartbeatAt": "2023-12-23T12:52:12.389569",
5
+ "startedAt": "2023-12-23T12:52:09.884051",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [],
9
+ "state": "running",
10
+ "program": "falcon_financial_finetuning.ipynb",
11
+ "codePathLocal": null,
12
+ "colab": "https://colab.research.google.com/notebook#fileId=1Wrk8K8X1p4XNKtZeX4rFgUqxQB3WPL1M",
13
+ "host": "e914d23c8e31",
14
+ "username": "root",
15
+ "executable": "/usr/bin/python3",
16
+ "cpu_count": 1,
17
+ "cpu_count_logical": 2,
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
+ "disk": {
36
+ "/": {
37
+ "total": 78.1898422241211,
38
+ "used": 40.1796989440918
39
+ }
40
+ },
41
+ "gpu": "Tesla T4",
42
+ "gpu_count": 1,
43
+ "gpu_devices": [
44
+ {
45
+ "name": "Tesla T4",
46
+ "memory_total": 16106127360
47
+ }
48
+ ],
49
+ "memory": {
50
+ "total": 12.674781799316406
51
+ }
52
+ }
wandb/run-20231223_125209-wzwtpkqz/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/loss": 1.9202, "train/learning_rate": 0.00019594929736144976, "train/epoch": 0.65, "train/global_step": 10, "_timestamp": 1703336025.8026273, "_runtime": 95.87209129333496, "_step": 0}
wandb/run-20231223_125209-wzwtpkqz/logs/debug-internal.log ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-12-23 12:52:09,951 INFO StreamThr :4184 [internal.py:wandb_internal():86] W&B internal server running at pid: 4184, started at: 2023-12-23 12:52:09.937331
2
+ 2023-12-23 12:52:09,956 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status
3
+ 2023-12-23 12:52:11,771 INFO WriterThread:4184 [datastore.py:open_for_write():85] open: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/run-wzwtpkqz.wandb
4
+ 2023-12-23 12:52:11,774 DEBUG SenderThread:4184 [sender.py:send():382] send: header
5
+ 2023-12-23 12:52:11,783 DEBUG SenderThread:4184 [sender.py:send():382] send: run
6
+ 2023-12-23 12:52:12,213 INFO SenderThread:4184 [dir_watcher.py:__init__():211] watching files in: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files
7
+ 2023-12-23 12:52:12,213 INFO SenderThread:4184 [sender.py:_start_run_threads():1136] run started: wzwtpkqz with start time 1703335929.930536
8
+ 2023-12-23 12:52:12,224 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: check_version
9
+ 2023-12-23 12:52:12,225 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: check_version
10
+ 2023-12-23 12:52:12,369 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: run_start
11
+ 2023-12-23 12:52:12,379 DEBUG HandlerThread:4184 [system_info.py:__init__():32] System info init
12
+ 2023-12-23 12:52:12,379 DEBUG HandlerThread:4184 [system_info.py:__init__():47] System info init done
13
+ 2023-12-23 12:52:12,380 INFO HandlerThread:4184 [system_monitor.py:start():194] Starting system monitor
14
+ 2023-12-23 12:52:12,380 INFO SystemMonitor:4184 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
+ 2023-12-23 12:52:12,380 INFO HandlerThread:4184 [system_monitor.py:probe():214] Collecting system info
16
+ 2023-12-23 12:52:12,381 INFO SystemMonitor:4184 [interfaces.py:start():190] Started cpu monitoring
17
+ 2023-12-23 12:52:12,382 INFO SystemMonitor:4184 [interfaces.py:start():190] Started disk monitoring
18
+ 2023-12-23 12:52:12,385 INFO SystemMonitor:4184 [interfaces.py:start():190] Started gpu monitoring
19
+ 2023-12-23 12:52:12,386 INFO SystemMonitor:4184 [interfaces.py:start():190] Started memory monitoring
20
+ 2023-12-23 12:52:12,386 INFO SystemMonitor:4184 [interfaces.py:start():190] Started network monitoring
21
+ 2023-12-23 12:52:12,389 DEBUG HandlerThread:4184 [system_info.py:probe():196] Probing system
22
+ 2023-12-23 12:52:12,394 DEBUG HandlerThread:4184 [gitlib.py:_init_repo():56] git repository is invalid
23
+ 2023-12-23 12:52:12,394 DEBUG HandlerThread:4184 [system_info.py:probe():244] Probing system done
24
+ 2023-12-23 12:52:12,394 DEBUG HandlerThread:4184 [system_monitor.py:probe():223] {'os': 'Linux-6.1.58+-x86_64-with-glibc2.35', 'python': '3.10.12', 'heartbeatAt': '2023-12-23T12:52:12.389569', 'startedAt': '2023-12-23T12:52:09.884051', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'falcon_financial_finetuning.ipynb', 'codePathLocal': None, 'colab': 'https://colab.research.google.com/notebook#fileId=1Wrk8K8X1p4XNKtZeX4rFgUqxQB3WPL1M', 'host': 'e914d23c8e31', 'username': 'root', 'executable': '/usr/bin/python3', 'cpu_count': 1, 'cpu_count_logical': 2, '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}], 'disk': {'/': {'total': 78.1898422241211, 'used': 40.1796989440918}}, 'gpu': 'Tesla T4', 'gpu_count': 1, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 12.674781799316406}}
25
+ 2023-12-23 12:52:12,394 INFO HandlerThread:4184 [system_monitor.py:probe():224] Finished collecting system info
26
+ 2023-12-23 12:52:12,395 INFO HandlerThread:4184 [system_monitor.py:probe():227] Publishing system info
27
+ 2023-12-23 12:52:12,395 DEBUG HandlerThread:4184 [system_info.py:_save_pip():52] Saving list of pip packages installed into the current environment
28
+ 2023-12-23 12:52:12,399 DEBUG HandlerThread:4184 [system_info.py:_save_pip():68] Saving pip packages done
29
+ 2023-12-23 12:52:12,403 INFO HandlerThread:4184 [system_monitor.py:probe():229] Finished publishing system info
30
+ 2023-12-23 12:52:12,429 DEBUG SenderThread:4184 [sender.py:send():382] send: files
31
+ 2023-12-23 12:52:12,429 INFO SenderThread:4184 [sender.py:_save_file():1392] saving file wandb-metadata.json with policy now
32
+ 2023-12-23 12:52:12,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
33
+ 2023-12-23 12:52:12,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
34
+ 2023-12-23 12:52:12,456 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
35
+ 2023-12-23 12:52:12,673 DEBUG SenderThread:4184 [sender.py:send():382] send: telemetry
36
+ 2023-12-23 12:52:12,674 DEBUG SenderThread:4184 [sender.py:send():382] send: config
37
+ 2023-12-23 12:52:12,675 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
38
+ 2023-12-23 12:52:12,676 DEBUG SenderThread:4184 [sender.py:send():382] send: telemetry
39
+ 2023-12-23 12:52:12,676 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
40
+ 2023-12-23 12:52:12,676 WARNING SenderThread:4184 [sender.py:send_metric():1343] Seen metric with glob (shouldn't happen)
41
+ 2023-12-23 12:52:12,676 DEBUG SenderThread:4184 [sender.py:send():382] send: telemetry
42
+ 2023-12-23 12:52:12,955 INFO wandb-upload_0:4184 [upload_job.py:push():131] Uploaded file /tmp/tmpk8by8xfswandb/i7g1zhkv-wandb-metadata.json
43
+ 2023-12-23 12:52:13,218 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/wandb-metadata.json
44
+ 2023-12-23 12:52:13,218 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/requirements.txt
45
+ 2023-12-23 12:52:13,219 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/output.log
46
+ 2023-12-23 12:52:15,680 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
47
+ 2023-12-23 12:52:20,681 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
48
+ 2023-12-23 12:52:25,682 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
49
+ 2023-12-23 12:52:27,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
50
+ 2023-12-23 12:52:27,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
51
+ 2023-12-23 12:52:27,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
52
+ 2023-12-23 12:52:31,606 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
53
+ 2023-12-23 12:52:36,606 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
54
+ 2023-12-23 12:52:41,614 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
55
+ 2023-12-23 12:52:42,269 INFO Thread-12 :4184 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/config.yaml
56
+ 2023-12-23 12:52:42,456 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
57
+ 2023-12-23 12:52:42,456 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
58
+ 2023-12-23 12:52:42,457 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
59
+ 2023-12-23 12:52:47,544 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
60
+ 2023-12-23 12:52:52,545 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
61
+ 2023-12-23 12:52:57,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
62
+ 2023-12-23 12:52:57,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
63
+ 2023-12-23 12:52:57,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
64
+ 2023-12-23 12:52:57,584 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
65
+ 2023-12-23 12:53:02,584 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
66
+ 2023-12-23 12:53:07,585 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
67
+ 2023-12-23 12:53:12,387 DEBUG SystemMonitor:4184 [system_monitor.py:_start():172] Starting system metrics aggregation loop
68
+ 2023-12-23 12:53:12,388 DEBUG SenderThread:4184 [sender.py:send():382] send: stats
69
+ 2023-12-23 12:53:12,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
70
+ 2023-12-23 12:53:12,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
71
+ 2023-12-23 12:53:12,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
72
+ 2023-12-23 12:53:12,620 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
73
+ 2023-12-23 12:53:17,621 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
74
+ 2023-12-23 12:53:22,622 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
75
+ 2023-12-23 12:53:27,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
76
+ 2023-12-23 12:53:27,456 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
77
+ 2023-12-23 12:53:27,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
78
+ 2023-12-23 12:53:27,625 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
79
+ 2023-12-23 12:53:32,626 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
80
+ 2023-12-23 12:53:37,626 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
81
+ 2023-12-23 12:53:42,389 DEBUG SenderThread:4184 [sender.py:send():382] send: stats
82
+ 2023-12-23 12:53:42,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
83
+ 2023-12-23 12:53:42,455 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
84
+ 2023-12-23 12:53:42,495 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
85
+ 2023-12-23 12:53:43,569 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
86
+ 2023-12-23 12:53:45,806 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: partial_history
87
+ 2023-12-23 12:53:45,809 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
88
+ 2023-12-23 12:53:45,809 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
89
+ 2023-12-23 12:53:45,810 DEBUG SenderThread:4184 [sender.py:send():382] send: metric
90
+ 2023-12-23 12:53:45,810 DEBUG SenderThread:4184 [sender.py:send():382] send: history
91
+ 2023-12-23 12:53:45,810 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: summary_record
92
+ 2023-12-23 12:53:45,814 INFO SenderThread:4184 [sender.py:_save_file():1392] saving file wandb-summary.json with policy end
93
+ 2023-12-23 12:53:46,399 INFO Thread-12 :4184 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/wandb-summary.json
94
+ 2023-12-23 12:53:48,816 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
95
+ 2023-12-23 12:53:53,817 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
96
+ 2023-12-23 12:53:54,502 INFO Thread-12 :4184 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/files/output.log
97
+ 2023-12-23 12:53:57,455 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: stop_status
98
+ 2023-12-23 12:53:57,456 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: internal_messages
99
+ 2023-12-23 12:53:57,457 DEBUG SenderThread:4184 [sender.py:send_request():409] send_request: stop_status
100
+ 2023-12-23 12:53:59,685 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
101
+ 2023-12-23 12:54:04,686 DEBUG HandlerThread:4184 [handler.py:handle_request():146] handle_request: status_report
wandb/run-20231223_125209-wzwtpkqz/logs/debug.log ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-12-23 12:52:09,917 INFO MainThread:1666 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
2
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Configure stats pid to 1666
3
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Loading settings from /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/settings
5
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
+ 2023-12-23 12:52:09,918 INFO MainThread:1666 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
9
+ 2023-12-23 12:52:09,919 INFO MainThread:1666 [wandb_init.py:_log_setup():524] Logging user logs to /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/logs/debug.log
10
+ 2023-12-23 12:52:09,919 INFO MainThread:1666 [wandb_init.py:_log_setup():525] Logging internal logs to /content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/wandb/run-20231223_125209-wzwtpkqz/logs/debug-internal.log
11
+ 2023-12-23 12:52:09,920 INFO MainThread:1666 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7ce3202b90f0>
12
+ 2023-12-23 12:52:09,920 INFO MainThread:1666 [wandb_init.py:init():564] calling init triggers
13
+ 2023-12-23 12:52:09,921 INFO MainThread:1666 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
14
+ config: {}
15
+ 2023-12-23 12:52:09,921 INFO MainThread:1666 [wandb_init.py:init():614] starting backend
16
+ 2023-12-23 12:52:09,921 INFO MainThread:1666 [wandb_init.py:init():618] setting up manager
17
+ 2023-12-23 12:52:09,928 INFO MainThread:1666 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2023-12-23 12:52:09,930 INFO MainThread:1666 [wandb_init.py:init():624] backend started and connected
19
+ 2023-12-23 12:52:09,979 INFO MainThread:1666 [wandb_run.py:_label_probe_notebook():1294] probe notebook
20
+ 2023-12-23 12:52:11,770 INFO MainThread:1666 [wandb_init.py:init():716] updated telemetry
21
+ 2023-12-23 12:52:11,782 INFO MainThread:1666 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
22
+ 2023-12-23 12:52:12,224 INFO MainThread:1666 [wandb_run.py:_on_init():2254] communicating current version
23
+ 2023-12-23 12:52:12,358 INFO MainThread:1666 [wandb_run.py:_on_init():2263] got version response
24
+ 2023-12-23 12:52:12,359 INFO MainThread:1666 [wandb_init.py:init():800] starting run threads in backend
25
+ 2023-12-23 12:52:12,454 INFO MainThread:1666 [wandb_run.py:_console_start():2233] atexit reg
26
+ 2023-12-23 12:52:12,455 INFO MainThread:1666 [wandb_run.py:_redirect():2088] redirect: wrap_raw
27
+ 2023-12-23 12:52:12,455 INFO MainThread:1666 [wandb_run.py:_redirect():2153] Wrapping output streams.
28
+ 2023-12-23 12:52:12,455 INFO MainThread:1666 [wandb_run.py:_redirect():2178] Redirects installed.
29
+ 2023-12-23 12:52:12,457 INFO MainThread:1666 [wandb_init.py:init():841] run started, returning control to user process
30
+ 2023-12-23 12:52:12,466 INFO MainThread:1666 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 65024, 'hidden_size': 4544, 'num_hidden_layers': 32, 'num_attention_heads': 71, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 11, 'eos_token_id': 11, 'num_kv_heads': 71, 'alibi': False, 'new_decoder_architecture': False, 'multi_query': True, 'parallel_attn': True, 'bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, '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, 'chunk_size_feed_forward': 0, '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': ['FalconForCausalLM'], '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': None, 'problem_type': None, '_name_or_path': 'tiiuae/falcon-7b', 'transformers_version': '4.36.2', 'apply_residual_connection_post_layernorm': False, 'auto_map': {'AutoConfig': 'tiiuae/falcon-7b--configuration_falcon.FalconConfig', 'AutoModel': 'tiiuae/falcon-7b--modeling_falcon.FalconModel', 'AutoModelForSequenceClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification', 'AutoModelForTokenClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification', 'AutoModelForQuestionAnswering': 'tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering', 'AutoModelForCausalLM': 'tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM'}, 'model_type': 'falcon', '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': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial', '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': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 80, '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': '/content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial/runs/Dec23_12-50-32_e914d23c8e31', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, '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': False, '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': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/falcon-7b-sharded-bf16-finetuned-financial', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, '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': True, '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': False, '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': False, '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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
wandb/run-20231223_125209-wzwtpkqz/run-wzwtpkqz.wandb ADDED
File without changes