csujeong commited on
Commit
18e70bc
1 Parent(s): 4e2d428

Training in progress, step 10

Browse files
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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
+ "k_proj",
23
+ "o_proj",
24
+ "v_proj",
25
+ "gate_proj",
26
+ "q_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80bd033cdce21f0462c1e5f89e23ac1aadea590fd5bd421e43eeec3e7b0cdd23
3
+ size 184592616
runs/Jan02_13-42-45_915b2a0951c7/events.out.tfevents.1704203002.915b2a0951c7.301.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12e3075581fc689283ea5da072d8cb3e034721ca8e3939096c0fe4c18b7a9b8
3
+ size 5030
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9127fd5e08dc4b85b72bd939640da72b261c353644bdfad63bee53cb49b1985c
3
+ size 4792
wandb/debug-internal.log ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-01-02 13:43:38,628 INFO StreamThr :8161 [internal.py:wandb_internal():86] W&B internal server running at pid: 8161, started at: 2024-01-02 13:43:38.611705
2
+ 2024-01-02 13:43:38,641 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status
3
+ 2024-01-02 13:43:41,130 INFO WriterThread:8161 [datastore.py:open_for_write():85] open: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/run-rjem4mwk.wandb
4
+ 2024-01-02 13:43:41,136 DEBUG SenderThread:8161 [sender.py:send():382] send: header
5
+ 2024-01-02 13:43:41,141 DEBUG SenderThread:8161 [sender.py:send():382] send: run
6
+ 2024-01-02 13:43:41,407 INFO SenderThread:8161 [dir_watcher.py:__init__():211] watching files in: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files
7
+ 2024-01-02 13:43:41,407 INFO SenderThread:8161 [sender.py:_start_run_threads():1136] run started: rjem4mwk with start time 1704203018.614629
8
+ 2024-01-02 13:43:41,418 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: check_version
9
+ 2024-01-02 13:43:41,419 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: check_version
10
+ 2024-01-02 13:43:41,586 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: run_start
11
+ 2024-01-02 13:43:41,597 DEBUG HandlerThread:8161 [system_info.py:__init__():32] System info init
12
+ 2024-01-02 13:43:41,597 DEBUG HandlerThread:8161 [system_info.py:__init__():47] System info init done
13
+ 2024-01-02 13:43:41,597 INFO HandlerThread:8161 [system_monitor.py:start():194] Starting system monitor
14
+ 2024-01-02 13:43:41,598 INFO SystemMonitor:8161 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
+ 2024-01-02 13:43:41,598 INFO HandlerThread:8161 [system_monitor.py:probe():214] Collecting system info
16
+ 2024-01-02 13:43:41,599 INFO SystemMonitor:8161 [interfaces.py:start():190] Started cpu monitoring
17
+ 2024-01-02 13:43:41,599 INFO SystemMonitor:8161 [interfaces.py:start():190] Started disk monitoring
18
+ 2024-01-02 13:43:41,601 INFO SystemMonitor:8161 [interfaces.py:start():190] Started gpu monitoring
19
+ 2024-01-02 13:43:41,602 INFO SystemMonitor:8161 [interfaces.py:start():190] Started memory monitoring
20
+ 2024-01-02 13:43:41,602 INFO SystemMonitor:8161 [interfaces.py:start():190] Started network monitoring
21
+ 2024-01-02 13:43:41,611 DEBUG HandlerThread:8161 [system_info.py:probe():196] Probing system
22
+ 2024-01-02 13:43:41,617 DEBUG HandlerThread:8161 [gitlib.py:_init_repo():56] git repository is invalid
23
+ 2024-01-02 13:43:41,617 DEBUG HandlerThread:8161 [system_info.py:probe():244] Probing system done
24
+ 2024-01-02 13:43:41,617 DEBUG HandlerThread:8161 [system_monitor.py:probe():223] {'os': 'Linux-6.1.58+-x86_64-with-glibc2.35', 'python': '3.10.12', 'heartbeatAt': '2024-01-02T13:43:41.611967', 'startedAt': '2024-01-02T13:43:38.531353', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'Mistral-7B-Finetuning-Stock.ipynb', 'codePathLocal': None, 'colab': 'https://colab.research.google.com/notebook#fileId=1AQD4_oNDDeA0MG56DfC3rfsBU6gn8Wr2', 'host': '915b2a0951c7', 'username': 'root', 'executable': '/usr/bin/python3', 'cpu_count': 1, 'cpu_count_logical': 2, 'cpu_freq': {'current': 2299.998, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2299.998, 'min': 0.0, 'max': 0.0}, {'current': 2299.998, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 78.1898422241211, 'used': 47.44428253173828}}, 'gpu': 'Tesla T4', 'gpu_count': 1, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 12.674789428710938}}
25
+ 2024-01-02 13:43:41,617 INFO HandlerThread:8161 [system_monitor.py:probe():224] Finished collecting system info
26
+ 2024-01-02 13:43:41,618 INFO HandlerThread:8161 [system_monitor.py:probe():227] Publishing system info
27
+ 2024-01-02 13:43:41,618 DEBUG HandlerThread:8161 [system_info.py:_save_pip():52] Saving list of pip packages installed into the current environment
28
+ 2024-01-02 13:43:41,625 DEBUG HandlerThread:8161 [system_info.py:_save_pip():68] Saving pip packages done
29
+ 2024-01-02 13:43:41,646 INFO HandlerThread:8161 [system_monitor.py:probe():229] Finished publishing system info
30
+ 2024-01-02 13:43:41,660 DEBUG SenderThread:8161 [sender.py:send():382] send: files
31
+ 2024-01-02 13:43:41,660 INFO SenderThread:8161 [sender.py:_save_file():1392] saving file wandb-metadata.json with policy now
32
+ 2024-01-02 13:43:41,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
33
+ 2024-01-02 13:43:41,690 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
34
+ 2024-01-02 13:43:41,693 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
35
+ 2024-01-02 13:43:41,985 DEBUG SenderThread:8161 [sender.py:send():382] send: telemetry
36
+ 2024-01-02 13:43:41,986 DEBUG SenderThread:8161 [sender.py:send():382] send: config
37
+ 2024-01-02 13:43:41,987 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
38
+ 2024-01-02 13:43:41,987 DEBUG SenderThread:8161 [sender.py:send():382] send: telemetry
39
+ 2024-01-02 13:43:41,988 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
40
+ 2024-01-02 13:43:41,988 WARNING SenderThread:8161 [sender.py:send_metric():1343] Seen metric with glob (shouldn't happen)
41
+ 2024-01-02 13:43:41,988 DEBUG SenderThread:8161 [sender.py:send():382] send: telemetry
42
+ 2024-01-02 13:43:42,021 INFO wandb-upload_0:8161 [upload_job.py:push():131] Uploaded file /tmp/tmpq1g9by67wandb/ve5qdbls-wandb-metadata.json
43
+ 2024-01-02 13:43:42,412 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/requirements.txt
44
+ 2024-01-02 13:43:42,413 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/wandb-metadata.json
45
+ 2024-01-02 13:43:42,413 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/output.log
46
+ 2024-01-02 13:43:43,992 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
47
+ 2024-01-02 13:43:48,993 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
48
+ 2024-01-02 13:43:53,994 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
49
+ 2024-01-02 13:43:56,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
50
+ 2024-01-02 13:43:56,691 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
51
+ 2024-01-02 13:43:56,691 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
52
+ 2024-01-02 13:43:59,738 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
53
+ 2024-01-02 13:44:04,739 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
54
+ 2024-01-02 13:44:09,749 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
55
+ 2024-01-02 13:44:10,481 INFO Thread-12 :8161 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/config.yaml
56
+ 2024-01-02 13:44:11,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
57
+ 2024-01-02 13:44:11,691 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
58
+ 2024-01-02 13:44:11,730 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
59
+ 2024-01-02 13:44:15,811 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
60
+ 2024-01-02 13:44:20,812 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
61
+ 2024-01-02 13:44:25,813 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
62
+ 2024-01-02 13:44:26,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
63
+ 2024-01-02 13:44:26,691 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
64
+ 2024-01-02 13:44:26,730 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
65
+ 2024-01-02 13:44:31,781 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
66
+ 2024-01-02 13:44:36,758 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: partial_history
67
+ 2024-01-02 13:44:36,760 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
68
+ 2024-01-02 13:44:36,761 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
69
+ 2024-01-02 13:44:36,761 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
70
+ 2024-01-02 13:44:36,761 DEBUG SenderThread:8161 [sender.py:send():382] send: history
71
+ 2024-01-02 13:44:36,762 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: summary_record
72
+ 2024-01-02 13:44:36,770 INFO SenderThread:8161 [sender.py:_save_file():1392] saving file wandb-summary.json with policy end
73
+ 2024-01-02 13:44:37,549 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/wandb-summary.json
74
+ 2024-01-02 13:44:37,773 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
75
+ 2024-01-02 13:44:41,603 DEBUG SystemMonitor:8161 [system_monitor.py:_start():172] Starting system metrics aggregation loop
76
+ 2024-01-02 13:44:41,604 DEBUG SenderThread:8161 [sender.py:send():382] send: stats
77
+ 2024-01-02 13:44:41,698 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
78
+ 2024-01-02 13:44:41,699 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
79
+ 2024-01-02 13:44:41,704 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
80
+ 2024-01-02 13:44:43,762 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
81
+ 2024-01-02 13:44:44,858 INFO Thread-12 :8161 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/config.yaml
82
+ 2024-01-02 13:44:45,860 INFO Thread-12 :8161 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/output.log
83
+ 2024-01-02 13:44:48,903 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
wandb/debug.log ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-01-02 13:43:38,600 INFO MainThread:301 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
2
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Configure stats pid to 301
3
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Loading settings from /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/settings
5
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
9
+ 2024-01-02 13:43:38,602 INFO MainThread:301 [wandb_init.py:_log_setup():524] Logging user logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/logs/debug.log
10
+ 2024-01-02 13:43:38,602 INFO MainThread:301 [wandb_init.py:_log_setup():525] Logging internal logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/logs/debug-internal.log
11
+ 2024-01-02 13:43:38,603 INFO MainThread:301 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7b728cc2c340>
12
+ 2024-01-02 13:43:38,603 INFO MainThread:301 [wandb_init.py:init():564] calling init triggers
13
+ 2024-01-02 13:43:38,604 INFO MainThread:301 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
14
+ config: {}
15
+ 2024-01-02 13:43:38,604 INFO MainThread:301 [wandb_init.py:init():614] starting backend
16
+ 2024-01-02 13:43:38,604 INFO MainThread:301 [wandb_init.py:init():618] setting up manager
17
+ 2024-01-02 13:43:38,608 INFO MainThread:301 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-01-02 13:43:38,612 INFO MainThread:301 [wandb_init.py:init():624] backend started and connected
19
+ 2024-01-02 13:43:38,659 INFO MainThread:301 [wandb_run.py:_label_probe_notebook():1294] probe notebook
20
+ 2024-01-02 13:43:41,129 INFO MainThread:301 [wandb_init.py:init():716] updated telemetry
21
+ 2024-01-02 13:43:41,139 INFO MainThread:301 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
22
+ 2024-01-02 13:43:41,418 INFO MainThread:301 [wandb_run.py:_on_init():2254] communicating current version
23
+ 2024-01-02 13:43:41,575 INFO MainThread:301 [wandb_run.py:_on_init():2263] got version response
24
+ 2024-01-02 13:43:41,575 INFO MainThread:301 [wandb_init.py:init():800] starting run threads in backend
25
+ 2024-01-02 13:43:41,690 INFO MainThread:301 [wandb_run.py:_console_start():2233] atexit reg
26
+ 2024-01-02 13:43:41,690 INFO MainThread:301 [wandb_run.py:_redirect():2088] redirect: wrap_raw
27
+ 2024-01-02 13:43:41,691 INFO MainThread:301 [wandb_run.py:_redirect():2153] Wrapping output streams.
28
+ 2024-01-02 13:43:41,691 INFO MainThread:301 [wandb_run.py:_redirect():2178] Redirects installed.
29
+ 2024-01-02 13:43:41,693 INFO MainThread:301 [wandb_init.py:init():841] run started, returning control to user process
30
+ 2024-01-02 13:43:41,699 INFO MainThread:301 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, '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': False, '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': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.37.0.dev0', 'model_type': 'mistral', '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/Mistral-7B-Finetuning-Stock', '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': 60, '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/Mistral-7B-Finetuning-Stock/runs/Jan02_13-42-45_915b2a0951c7', '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/Mistral-7B-Finetuning-Stock', '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-20240102_134338-rjem4mwk/files/config.yaml ADDED
@@ -0,0 +1,657 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 4.37.0.dev0
10
+ is_jupyter_run: true
11
+ is_kaggle_kernel: false
12
+ start_time: 1704203018.614629
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: 4.37.0.dev0
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
+ - 1: train/loss
60
+ 5: 1
61
+ 6:
62
+ - 1
63
+ - 1: train/learning_rate
64
+ 5: 1
65
+ 6:
66
+ - 1
67
+ - 1: train/epoch
68
+ 5: 1
69
+ 6:
70
+ - 1
71
+ vocab_size:
72
+ desc: null
73
+ value: 32000
74
+ max_position_embeddings:
75
+ desc: null
76
+ value: 32768
77
+ hidden_size:
78
+ desc: null
79
+ value: 4096
80
+ intermediate_size:
81
+ desc: null
82
+ value: 14336
83
+ num_hidden_layers:
84
+ desc: null
85
+ value: 32
86
+ num_attention_heads:
87
+ desc: null
88
+ value: 32
89
+ sliding_window:
90
+ desc: null
91
+ value: 4096
92
+ num_key_value_heads:
93
+ desc: null
94
+ value: 8
95
+ hidden_act:
96
+ desc: null
97
+ value: silu
98
+ initializer_range:
99
+ desc: null
100
+ value: 0.02
101
+ rms_norm_eps:
102
+ desc: null
103
+ value: 1.0e-05
104
+ use_cache:
105
+ desc: null
106
+ value: false
107
+ rope_theta:
108
+ desc: null
109
+ value: 10000.0
110
+ attention_dropout:
111
+ desc: null
112
+ value: 0.0
113
+ return_dict:
114
+ desc: null
115
+ value: true
116
+ output_hidden_states:
117
+ desc: null
118
+ value: false
119
+ output_attentions:
120
+ desc: null
121
+ value: false
122
+ torchscript:
123
+ desc: null
124
+ value: false
125
+ torch_dtype:
126
+ desc: null
127
+ value: bfloat16
128
+ use_bfloat16:
129
+ desc: null
130
+ value: false
131
+ tf_legacy_loss:
132
+ desc: null
133
+ value: false
134
+ pruned_heads:
135
+ desc: null
136
+ value: {}
137
+ tie_word_embeddings:
138
+ desc: null
139
+ value: false
140
+ is_encoder_decoder:
141
+ desc: null
142
+ value: false
143
+ is_decoder:
144
+ desc: null
145
+ value: false
146
+ cross_attention_hidden_size:
147
+ desc: null
148
+ value: null
149
+ add_cross_attention:
150
+ desc: null
151
+ value: false
152
+ tie_encoder_decoder:
153
+ desc: null
154
+ value: false
155
+ max_length:
156
+ desc: null
157
+ value: 20
158
+ min_length:
159
+ desc: null
160
+ value: 0
161
+ do_sample:
162
+ desc: null
163
+ value: false
164
+ early_stopping:
165
+ desc: null
166
+ value: false
167
+ num_beams:
168
+ desc: null
169
+ value: 1
170
+ num_beam_groups:
171
+ desc: null
172
+ value: 1
173
+ diversity_penalty:
174
+ desc: null
175
+ value: 0.0
176
+ temperature:
177
+ desc: null
178
+ value: 1.0
179
+ top_k:
180
+ desc: null
181
+ value: 50
182
+ top_p:
183
+ desc: null
184
+ value: 1.0
185
+ typical_p:
186
+ desc: null
187
+ value: 1.0
188
+ repetition_penalty:
189
+ desc: null
190
+ value: 1.0
191
+ length_penalty:
192
+ desc: null
193
+ value: 1.0
194
+ no_repeat_ngram_size:
195
+ desc: null
196
+ value: 0
197
+ encoder_no_repeat_ngram_size:
198
+ desc: null
199
+ value: 0
200
+ bad_words_ids:
201
+ desc: null
202
+ value: null
203
+ num_return_sequences:
204
+ desc: null
205
+ value: 1
206
+ chunk_size_feed_forward:
207
+ desc: null
208
+ value: 0
209
+ output_scores:
210
+ desc: null
211
+ value: false
212
+ return_dict_in_generate:
213
+ desc: null
214
+ value: false
215
+ forced_bos_token_id:
216
+ desc: null
217
+ value: null
218
+ forced_eos_token_id:
219
+ desc: null
220
+ value: null
221
+ remove_invalid_values:
222
+ desc: null
223
+ value: false
224
+ exponential_decay_length_penalty:
225
+ desc: null
226
+ value: null
227
+ suppress_tokens:
228
+ desc: null
229
+ value: null
230
+ begin_suppress_tokens:
231
+ desc: null
232
+ value: null
233
+ architectures:
234
+ desc: null
235
+ value:
236
+ - MistralForCausalLM
237
+ finetuning_task:
238
+ desc: null
239
+ value: null
240
+ id2label:
241
+ desc: null
242
+ value:
243
+ '0': LABEL_0
244
+ '1': LABEL_1
245
+ label2id:
246
+ desc: null
247
+ value:
248
+ LABEL_0: 0
249
+ LABEL_1: 1
250
+ tokenizer_class:
251
+ desc: null
252
+ value: null
253
+ prefix:
254
+ desc: null
255
+ value: null
256
+ bos_token_id:
257
+ desc: null
258
+ value: 1
259
+ pad_token_id:
260
+ desc: null
261
+ value: null
262
+ eos_token_id:
263
+ desc: null
264
+ value: 2
265
+ sep_token_id:
266
+ desc: null
267
+ value: null
268
+ decoder_start_token_id:
269
+ desc: null
270
+ value: null
271
+ task_specific_params:
272
+ desc: null
273
+ value: null
274
+ problem_type:
275
+ desc: null
276
+ value: null
277
+ _name_or_path:
278
+ desc: null
279
+ value: mistralai/Mistral-7B-v0.1
280
+ transformers_version:
281
+ desc: null
282
+ value: 4.37.0.dev0
283
+ model_type:
284
+ desc: null
285
+ value: mistral
286
+ quantization_config:
287
+ desc: null
288
+ value:
289
+ quant_method: QuantizationMethod.BITS_AND_BYTES
290
+ load_in_8bit: false
291
+ load_in_4bit: true
292
+ llm_int8_threshold: 6.0
293
+ llm_int8_skip_modules: null
294
+ llm_int8_enable_fp32_cpu_offload: false
295
+ llm_int8_has_fp16_weight: false
296
+ bnb_4bit_quant_type: nf4
297
+ bnb_4bit_use_double_quant: true
298
+ bnb_4bit_compute_dtype: bfloat16
299
+ output_dir:
300
+ desc: null
301
+ value: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock
302
+ overwrite_output_dir:
303
+ desc: null
304
+ value: false
305
+ do_train:
306
+ desc: null
307
+ value: false
308
+ do_eval:
309
+ desc: null
310
+ value: false
311
+ do_predict:
312
+ desc: null
313
+ value: false
314
+ evaluation_strategy:
315
+ desc: null
316
+ value: 'no'
317
+ prediction_loss_only:
318
+ desc: null
319
+ value: false
320
+ per_device_train_batch_size:
321
+ desc: null
322
+ value: 2
323
+ per_device_eval_batch_size:
324
+ desc: null
325
+ value: 8
326
+ per_gpu_train_batch_size:
327
+ desc: null
328
+ value: null
329
+ per_gpu_eval_batch_size:
330
+ desc: null
331
+ value: null
332
+ gradient_accumulation_steps:
333
+ desc: null
334
+ value: 2
335
+ eval_accumulation_steps:
336
+ desc: null
337
+ value: null
338
+ eval_delay:
339
+ desc: null
340
+ value: 0
341
+ learning_rate:
342
+ desc: null
343
+ value: 0.0002
344
+ weight_decay:
345
+ desc: null
346
+ value: 0.0
347
+ adam_beta1:
348
+ desc: null
349
+ value: 0.9
350
+ adam_beta2:
351
+ desc: null
352
+ value: 0.999
353
+ adam_epsilon:
354
+ desc: null
355
+ value: 1.0e-08
356
+ max_grad_norm:
357
+ desc: null
358
+ value: 0.3
359
+ num_train_epochs:
360
+ desc: null
361
+ value: 3.0
362
+ max_steps:
363
+ desc: null
364
+ value: 60
365
+ lr_scheduler_type:
366
+ desc: null
367
+ value: cosine
368
+ lr_scheduler_kwargs:
369
+ desc: null
370
+ value: {}
371
+ warmup_ratio:
372
+ desc: null
373
+ value: 0.03
374
+ warmup_steps:
375
+ desc: null
376
+ value: 0
377
+ log_level:
378
+ desc: null
379
+ value: passive
380
+ log_level_replica:
381
+ desc: null
382
+ value: warning
383
+ log_on_each_node:
384
+ desc: null
385
+ value: true
386
+ logging_dir:
387
+ desc: null
388
+ value: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/runs/Jan02_13-42-45_915b2a0951c7
389
+ logging_strategy:
390
+ desc: null
391
+ value: steps
392
+ logging_first_step:
393
+ desc: null
394
+ value: false
395
+ logging_steps:
396
+ desc: null
397
+ value: 10
398
+ logging_nan_inf_filter:
399
+ desc: null
400
+ value: true
401
+ save_strategy:
402
+ desc: null
403
+ value: steps
404
+ save_steps:
405
+ desc: null
406
+ value: 10
407
+ save_total_limit:
408
+ desc: null
409
+ value: null
410
+ save_safetensors:
411
+ desc: null
412
+ value: true
413
+ save_on_each_node:
414
+ desc: null
415
+ value: false
416
+ save_only_model:
417
+ desc: null
418
+ value: false
419
+ no_cuda:
420
+ desc: null
421
+ value: false
422
+ use_cpu:
423
+ desc: null
424
+ value: false
425
+ use_mps_device:
426
+ desc: null
427
+ value: false
428
+ seed:
429
+ desc: null
430
+ value: 42
431
+ data_seed:
432
+ desc: null
433
+ value: null
434
+ jit_mode_eval:
435
+ desc: null
436
+ value: false
437
+ use_ipex:
438
+ desc: null
439
+ value: false
440
+ bf16:
441
+ desc: null
442
+ value: false
443
+ fp16:
444
+ desc: null
445
+ value: false
446
+ fp16_opt_level:
447
+ desc: null
448
+ value: O1
449
+ half_precision_backend:
450
+ desc: null
451
+ value: auto
452
+ bf16_full_eval:
453
+ desc: null
454
+ value: false
455
+ fp16_full_eval:
456
+ desc: null
457
+ value: false
458
+ tf32:
459
+ desc: null
460
+ value: false
461
+ local_rank:
462
+ desc: null
463
+ value: 0
464
+ ddp_backend:
465
+ desc: null
466
+ value: null
467
+ tpu_num_cores:
468
+ desc: null
469
+ value: null
470
+ tpu_metrics_debug:
471
+ desc: null
472
+ value: false
473
+ debug:
474
+ desc: null
475
+ value: []
476
+ dataloader_drop_last:
477
+ desc: null
478
+ value: false
479
+ eval_steps:
480
+ desc: null
481
+ value: null
482
+ dataloader_num_workers:
483
+ desc: null
484
+ value: 0
485
+ past_index:
486
+ desc: null
487
+ value: -1
488
+ run_name:
489
+ desc: null
490
+ value: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock
491
+ disable_tqdm:
492
+ desc: null
493
+ value: false
494
+ remove_unused_columns:
495
+ desc: null
496
+ value: true
497
+ label_names:
498
+ desc: null
499
+ value: null
500
+ load_best_model_at_end:
501
+ desc: null
502
+ value: false
503
+ metric_for_best_model:
504
+ desc: null
505
+ value: null
506
+ greater_is_better:
507
+ desc: null
508
+ value: null
509
+ ignore_data_skip:
510
+ desc: null
511
+ value: false
512
+ fsdp:
513
+ desc: null
514
+ value: []
515
+ fsdp_min_num_params:
516
+ desc: null
517
+ value: 0
518
+ fsdp_config:
519
+ desc: null
520
+ value:
521
+ min_num_params: 0
522
+ xla: false
523
+ xla_fsdp_grad_ckpt: false
524
+ fsdp_transformer_layer_cls_to_wrap:
525
+ desc: null
526
+ value: null
527
+ deepspeed:
528
+ desc: null
529
+ value: null
530
+ label_smoothing_factor:
531
+ desc: null
532
+ value: 0.0
533
+ optim:
534
+ desc: null
535
+ value: paged_adamw_32bit
536
+ optim_args:
537
+ desc: null
538
+ value: null
539
+ adafactor:
540
+ desc: null
541
+ value: false
542
+ group_by_length:
543
+ desc: null
544
+ value: true
545
+ length_column_name:
546
+ desc: null
547
+ value: length
548
+ report_to:
549
+ desc: null
550
+ value:
551
+ - tensorboard
552
+ - wandb
553
+ ddp_find_unused_parameters:
554
+ desc: null
555
+ value: null
556
+ ddp_bucket_cap_mb:
557
+ desc: null
558
+ value: null
559
+ ddp_broadcast_buffers:
560
+ desc: null
561
+ value: null
562
+ dataloader_pin_memory:
563
+ desc: null
564
+ value: true
565
+ dataloader_persistent_workers:
566
+ desc: null
567
+ value: false
568
+ skip_memory_metrics:
569
+ desc: null
570
+ value: true
571
+ use_legacy_prediction_loop:
572
+ desc: null
573
+ value: false
574
+ push_to_hub:
575
+ desc: null
576
+ value: true
577
+ resume_from_checkpoint:
578
+ desc: null
579
+ value: null
580
+ hub_model_id:
581
+ desc: null
582
+ value: null
583
+ hub_strategy:
584
+ desc: null
585
+ value: every_save
586
+ hub_token:
587
+ desc: null
588
+ value: <HUB_TOKEN>
589
+ hub_private_repo:
590
+ desc: null
591
+ value: false
592
+ hub_always_push:
593
+ desc: null
594
+ value: false
595
+ gradient_checkpointing:
596
+ desc: null
597
+ value: false
598
+ gradient_checkpointing_kwargs:
599
+ desc: null
600
+ value: null
601
+ include_inputs_for_metrics:
602
+ desc: null
603
+ value: false
604
+ fp16_backend:
605
+ desc: null
606
+ value: auto
607
+ push_to_hub_model_id:
608
+ desc: null
609
+ value: null
610
+ push_to_hub_organization:
611
+ desc: null
612
+ value: null
613
+ push_to_hub_token:
614
+ desc: null
615
+ value: <PUSH_TO_HUB_TOKEN>
616
+ mp_parameters:
617
+ desc: null
618
+ value: ''
619
+ auto_find_batch_size:
620
+ desc: null
621
+ value: false
622
+ full_determinism:
623
+ desc: null
624
+ value: false
625
+ torchdynamo:
626
+ desc: null
627
+ value: null
628
+ ray_scope:
629
+ desc: null
630
+ value: last
631
+ ddp_timeout:
632
+ desc: null
633
+ value: 1800
634
+ torch_compile:
635
+ desc: null
636
+ value: false
637
+ torch_compile_backend:
638
+ desc: null
639
+ value: null
640
+ torch_compile_mode:
641
+ desc: null
642
+ value: null
643
+ dispatch_batches:
644
+ desc: null
645
+ value: null
646
+ split_batches:
647
+ desc: null
648
+ value: false
649
+ include_tokens_per_second:
650
+ desc: null
651
+ value: false
652
+ include_num_input_tokens_seen:
653
+ desc: null
654
+ value: false
655
+ neftune_noise_alpha:
656
+ desc: null
657
+ value: null
wandb/run-20240102_134338-rjem4mwk/files/output.log ADDED
@@ -0,0 +1 @@
 
 
1
+
wandb/run-20240102_134338-rjem4mwk/files/requirements.txt ADDED
@@ -0,0 +1,511 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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==2.16.1
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
+ nvidia-cublas-cu12==12.1.3.1
274
+ nvidia-cuda-cupti-cu12==12.1.105
275
+ nvidia-cuda-nvrtc-cu12==12.1.105
276
+ nvidia-cuda-runtime-cu12==12.1.105
277
+ nvidia-cudnn-cu12==8.9.2.26
278
+ nvidia-cufft-cu12==11.0.2.54
279
+ nvidia-curand-cu12==10.3.2.106
280
+ nvidia-cusolver-cu12==11.4.5.107
281
+ nvidia-cusparse-cu12==12.1.0.106
282
+ nvidia-nccl-cu12==2.18.1
283
+ nvidia-nvjitlink-cu12==12.3.101
284
+ nvidia-nvtx-cu12==12.1.105
285
+ oauth2client==4.1.3
286
+ oauthlib==3.2.2
287
+ opencv-contrib-python==4.8.0.76
288
+ opencv-python-headless==4.8.1.78
289
+ opencv-python==4.8.0.76
290
+ openpyxl==3.1.2
291
+ opt-einsum==3.3.0
292
+ optax==0.1.7
293
+ orbax-checkpoint==0.4.4
294
+ osqp==0.6.2.post8
295
+ packaging==23.2
296
+ pandas-datareader==0.10.0
297
+ pandas-gbq==0.19.2
298
+ pandas-stubs==1.5.3.230304
299
+ pandas==1.5.3
300
+ pandocfilters==1.5.0
301
+ panel==1.3.4
302
+ param==2.0.1
303
+ parso==0.8.3
304
+ parsy==2.1
305
+ partd==1.4.1
306
+ pathlib==1.0.1
307
+ pathy==0.10.3
308
+ patsy==0.5.4
309
+ peewee==3.17.0
310
+ peft==0.7.2.dev0
311
+ pexpect==4.9.0
312
+ pickleshare==0.7.5
313
+ pillow==9.4.0
314
+ pip-tools==6.13.0
315
+ pip==23.1.2
316
+ platformdirs==4.1.0
317
+ plotly==5.15.0
318
+ plotnine==0.12.4
319
+ pluggy==1.3.0
320
+ polars==0.17.3
321
+ pooch==1.8.0
322
+ portpicker==1.5.2
323
+ prefetch-generator==1.0.3
324
+ preshed==3.0.9
325
+ prettytable==3.9.0
326
+ proglog==0.1.10
327
+ progressbar2==4.2.0
328
+ prometheus-client==0.19.0
329
+ promise==2.3
330
+ prompt-toolkit==3.0.43
331
+ prophet==1.1.5
332
+ proto-plus==1.23.0
333
+ protobuf==3.20.3
334
+ psutil==5.9.5
335
+ psycopg2==2.9.9
336
+ ptyprocess==0.7.0
337
+ py-cpuinfo==9.0.0
338
+ py4j==0.10.9.7
339
+ pyarrow-hotfix==0.6
340
+ pyarrow==10.0.1
341
+ pyasn1-modules==0.3.0
342
+ pyasn1==0.5.1
343
+ pycocotools==2.0.7
344
+ pycparser==2.21
345
+ pyct==0.5.0
346
+ pydantic==1.10.13
347
+ pydata-google-auth==1.8.2
348
+ pydot-ng==2.0.0
349
+ pydot==1.4.2
350
+ pydotplus==2.0.2
351
+ pydrive2==1.6.3
352
+ pydrive==1.3.1
353
+ pyerfa==2.0.1.1
354
+ pygame==2.5.2
355
+ pygments==2.16.1
356
+ pygobject==3.42.1
357
+ pyjwt==2.3.0
358
+ pymc==5.7.2
359
+ pymystem3==0.2.0
360
+ pyopengl==3.1.7
361
+ pyopenssl==23.3.0
362
+ pyparsing==3.1.1
363
+ pyperclip==1.8.2
364
+ pyproj==3.6.1
365
+ pyproject-hooks==1.0.0
366
+ pyshp==2.3.1
367
+ pysocks==1.7.1
368
+ pytensor==2.14.2
369
+ pytest==7.4.3
370
+ python-apt==0.0.0
371
+ python-box==7.1.1
372
+ python-dateutil==2.8.2
373
+ python-louvain==0.16
374
+ python-slugify==8.0.1
375
+ python-utils==3.8.1
376
+ pytz==2023.3.post1
377
+ pyviz-comms==3.0.0
378
+ pywavelets==1.5.0
379
+ pyyaml==6.0.1
380
+ pyzmq==23.2.1
381
+ qdldl==0.1.7.post0
382
+ qudida==0.0.4
383
+ ratelim==0.1.6
384
+ referencing==0.32.0
385
+ regex==2023.6.3
386
+ requests-oauthlib==1.3.1
387
+ requests==2.31.0
388
+ requirements-parser==0.5.0
389
+ rich==13.7.0
390
+ rpds-py==0.15.2
391
+ rpy2==3.4.2
392
+ rsa==4.9
393
+ safetensors==0.4.1
394
+ scikit-image==0.19.3
395
+ scikit-learn==1.2.2
396
+ scipy==1.11.4
397
+ scooby==0.9.2
398
+ scs==3.2.4.post1
399
+ seaborn==0.12.2
400
+ secretstorage==3.3.1
401
+ send2trash==1.8.2
402
+ sentencepiece==0.1.99
403
+ sentry-sdk==1.39.1
404
+ setproctitle==1.3.3
405
+ setuptools==67.7.2
406
+ shapely==2.0.2
407
+ shtab==1.6.5
408
+ six==1.16.0
409
+ sklearn-pandas==2.2.0
410
+ smart-open==6.4.0
411
+ smmap==5.0.1
412
+ sniffio==1.3.0
413
+ snowballstemmer==2.2.0
414
+ sortedcontainers==2.4.0
415
+ soundfile==0.12.1
416
+ soupsieve==2.5
417
+ soxr==0.3.7
418
+ spacy-legacy==3.0.12
419
+ spacy-loggers==1.0.5
420
+ spacy==3.6.1
421
+ sphinx==5.0.2
422
+ sphinxcontrib-applehelp==1.0.7
423
+ sphinxcontrib-devhelp==1.0.5
424
+ sphinxcontrib-htmlhelp==2.0.4
425
+ sphinxcontrib-jsmath==1.0.1
426
+ sphinxcontrib-qthelp==1.0.6
427
+ sphinxcontrib-serializinghtml==1.1.9
428
+ sqlalchemy==2.0.23
429
+ sqlglot==17.16.2
430
+ sqlparse==0.4.4
431
+ srsly==2.4.8
432
+ stanio==0.3.0
433
+ statsmodels==0.14.1
434
+ sympy==1.12
435
+ tables==3.8.0
436
+ tabulate==0.9.0
437
+ tbb==2021.11.0
438
+ tblib==3.0.0
439
+ tenacity==8.2.3
440
+ tensorboard-data-server==0.7.2
441
+ tensorboard==2.15.1
442
+ tensorflow-datasets==4.9.4
443
+ tensorflow-estimator==2.15.0
444
+ tensorflow-gcs-config==2.15.0
445
+ tensorflow-hub==0.15.0
446
+ tensorflow-io-gcs-filesystem==0.34.0
447
+ tensorflow-metadata==1.14.0
448
+ tensorflow-probability==0.22.0
449
+ tensorflow==2.15.0
450
+ tensorstore==0.1.45
451
+ termcolor==2.4.0
452
+ terminado==0.18.0
453
+ text-unidecode==1.3
454
+ textblob==0.17.1
455
+ tf-slim==1.1.0
456
+ thinc==8.1.12
457
+ threadpoolctl==3.2.0
458
+ tifffile==2023.12.9
459
+ tinycss2==1.2.1
460
+ tokenizers==0.15.0
461
+ toml==0.10.2
462
+ tomli==2.0.1
463
+ toolz==0.12.0
464
+ torch==2.1.2
465
+ torchaudio==2.1.0+cu121
466
+ torchdata==0.7.0
467
+ torchsummary==1.5.1
468
+ torchtext==0.16.0
469
+ torchvision==0.16.0+cu121
470
+ tornado==6.3.2
471
+ tqdm==4.66.1
472
+ traitlets==5.7.1
473
+ traittypes==0.2.1
474
+ transformers==4.37.0.dev0
475
+ triton==2.1.0
476
+ trl==0.7.7
477
+ tweepy==4.14.0
478
+ typer==0.9.0
479
+ types-pytz==2023.3.1.1
480
+ types-setuptools==69.0.0.0
481
+ typing-extensions==4.5.0
482
+ tyro==0.6.3
483
+ tzlocal==5.2
484
+ uc-micro-py==1.0.2
485
+ uritemplate==4.1.1
486
+ urllib3==2.0.7
487
+ vega-datasets==0.9.0
488
+ wadllib==1.3.6
489
+ wandb==0.16.1
490
+ wasabi==1.1.2
491
+ wcwidth==0.2.12
492
+ webcolors==1.13
493
+ webencodings==0.5.1
494
+ websocket-client==1.7.0
495
+ werkzeug==3.0.1
496
+ wheel==0.42.0
497
+ widgetsnbextension==3.6.6
498
+ wordcloud==1.9.3
499
+ wrapt==1.14.1
500
+ xarray-einstats==0.6.0
501
+ xarray==2023.7.0
502
+ xformers==0.0.23.post1
503
+ xgboost==2.0.2
504
+ xlrd==2.0.1
505
+ xxhash==3.4.1
506
+ xyzservices==2023.10.1
507
+ yarl==1.9.4
508
+ yellowbrick==1.5
509
+ yfinance==0.2.33
510
+ zict==3.0.0
511
+ zipp==3.17.0
wandb/run-20240102_134338-rjem4mwk/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": "2024-01-02T13:43:41.611967",
5
+ "startedAt": "2024-01-02T13:43:38.531353",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [],
9
+ "state": "running",
10
+ "program": "Mistral-7B-Finetuning-Stock.ipynb",
11
+ "codePathLocal": null,
12
+ "colab": "https://colab.research.google.com/notebook#fileId=1AQD4_oNDDeA0MG56DfC3rfsBU6gn8Wr2",
13
+ "host": "915b2a0951c7",
14
+ "username": "root",
15
+ "executable": "/usr/bin/python3",
16
+ "cpu_count": 1,
17
+ "cpu_count_logical": 2,
18
+ "cpu_freq": {
19
+ "current": 2299.998,
20
+ "min": 0.0,
21
+ "max": 0.0
22
+ },
23
+ "cpu_freq_per_core": [
24
+ {
25
+ "current": 2299.998,
26
+ "min": 0.0,
27
+ "max": 0.0
28
+ },
29
+ {
30
+ "current": 2299.998,
31
+ "min": 0.0,
32
+ "max": 0.0
33
+ }
34
+ ],
35
+ "disk": {
36
+ "/": {
37
+ "total": 78.1898422241211,
38
+ "used": 47.44428253173828
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": 12.674789428710938
51
+ }
52
+ }
wandb/run-20240102_134338-rjem4mwk/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/loss": 1.5193, "train/learning_rate": 0.00019075754196709572, "train/epoch": 0.29, "train/global_step": 10, "_timestamp": 1704203076.75647, "_runtime": 58.14184093475342, "_step": 0}
wandb/run-20240102_134338-rjem4mwk/logs/debug-internal.log ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-01-02 13:43:38,628 INFO StreamThr :8161 [internal.py:wandb_internal():86] W&B internal server running at pid: 8161, started at: 2024-01-02 13:43:38.611705
2
+ 2024-01-02 13:43:38,641 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status
3
+ 2024-01-02 13:43:41,130 INFO WriterThread:8161 [datastore.py:open_for_write():85] open: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/run-rjem4mwk.wandb
4
+ 2024-01-02 13:43:41,136 DEBUG SenderThread:8161 [sender.py:send():382] send: header
5
+ 2024-01-02 13:43:41,141 DEBUG SenderThread:8161 [sender.py:send():382] send: run
6
+ 2024-01-02 13:43:41,407 INFO SenderThread:8161 [dir_watcher.py:__init__():211] watching files in: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files
7
+ 2024-01-02 13:43:41,407 INFO SenderThread:8161 [sender.py:_start_run_threads():1136] run started: rjem4mwk with start time 1704203018.614629
8
+ 2024-01-02 13:43:41,418 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: check_version
9
+ 2024-01-02 13:43:41,419 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: check_version
10
+ 2024-01-02 13:43:41,586 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: run_start
11
+ 2024-01-02 13:43:41,597 DEBUG HandlerThread:8161 [system_info.py:__init__():32] System info init
12
+ 2024-01-02 13:43:41,597 DEBUG HandlerThread:8161 [system_info.py:__init__():47] System info init done
13
+ 2024-01-02 13:43:41,597 INFO HandlerThread:8161 [system_monitor.py:start():194] Starting system monitor
14
+ 2024-01-02 13:43:41,598 INFO SystemMonitor:8161 [system_monitor.py:_start():158] Starting system asset monitoring threads
15
+ 2024-01-02 13:43:41,598 INFO HandlerThread:8161 [system_monitor.py:probe():214] Collecting system info
16
+ 2024-01-02 13:43:41,599 INFO SystemMonitor:8161 [interfaces.py:start():190] Started cpu monitoring
17
+ 2024-01-02 13:43:41,599 INFO SystemMonitor:8161 [interfaces.py:start():190] Started disk monitoring
18
+ 2024-01-02 13:43:41,601 INFO SystemMonitor:8161 [interfaces.py:start():190] Started gpu monitoring
19
+ 2024-01-02 13:43:41,602 INFO SystemMonitor:8161 [interfaces.py:start():190] Started memory monitoring
20
+ 2024-01-02 13:43:41,602 INFO SystemMonitor:8161 [interfaces.py:start():190] Started network monitoring
21
+ 2024-01-02 13:43:41,611 DEBUG HandlerThread:8161 [system_info.py:probe():196] Probing system
22
+ 2024-01-02 13:43:41,617 DEBUG HandlerThread:8161 [gitlib.py:_init_repo():56] git repository is invalid
23
+ 2024-01-02 13:43:41,617 DEBUG HandlerThread:8161 [system_info.py:probe():244] Probing system done
24
+ 2024-01-02 13:43:41,617 DEBUG HandlerThread:8161 [system_monitor.py:probe():223] {'os': 'Linux-6.1.58+-x86_64-with-glibc2.35', 'python': '3.10.12', 'heartbeatAt': '2024-01-02T13:43:41.611967', 'startedAt': '2024-01-02T13:43:38.531353', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'Mistral-7B-Finetuning-Stock.ipynb', 'codePathLocal': None, 'colab': 'https://colab.research.google.com/notebook#fileId=1AQD4_oNDDeA0MG56DfC3rfsBU6gn8Wr2', 'host': '915b2a0951c7', 'username': 'root', 'executable': '/usr/bin/python3', 'cpu_count': 1, 'cpu_count_logical': 2, 'cpu_freq': {'current': 2299.998, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2299.998, 'min': 0.0, 'max': 0.0}, {'current': 2299.998, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 78.1898422241211, 'used': 47.44428253173828}}, 'gpu': 'Tesla T4', 'gpu_count': 1, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 12.674789428710938}}
25
+ 2024-01-02 13:43:41,617 INFO HandlerThread:8161 [system_monitor.py:probe():224] Finished collecting system info
26
+ 2024-01-02 13:43:41,618 INFO HandlerThread:8161 [system_monitor.py:probe():227] Publishing system info
27
+ 2024-01-02 13:43:41,618 DEBUG HandlerThread:8161 [system_info.py:_save_pip():52] Saving list of pip packages installed into the current environment
28
+ 2024-01-02 13:43:41,625 DEBUG HandlerThread:8161 [system_info.py:_save_pip():68] Saving pip packages done
29
+ 2024-01-02 13:43:41,646 INFO HandlerThread:8161 [system_monitor.py:probe():229] Finished publishing system info
30
+ 2024-01-02 13:43:41,660 DEBUG SenderThread:8161 [sender.py:send():382] send: files
31
+ 2024-01-02 13:43:41,660 INFO SenderThread:8161 [sender.py:_save_file():1392] saving file wandb-metadata.json with policy now
32
+ 2024-01-02 13:43:41,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
33
+ 2024-01-02 13:43:41,690 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
34
+ 2024-01-02 13:43:41,693 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
35
+ 2024-01-02 13:43:41,985 DEBUG SenderThread:8161 [sender.py:send():382] send: telemetry
36
+ 2024-01-02 13:43:41,986 DEBUG SenderThread:8161 [sender.py:send():382] send: config
37
+ 2024-01-02 13:43:41,987 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
38
+ 2024-01-02 13:43:41,987 DEBUG SenderThread:8161 [sender.py:send():382] send: telemetry
39
+ 2024-01-02 13:43:41,988 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
40
+ 2024-01-02 13:43:41,988 WARNING SenderThread:8161 [sender.py:send_metric():1343] Seen metric with glob (shouldn't happen)
41
+ 2024-01-02 13:43:41,988 DEBUG SenderThread:8161 [sender.py:send():382] send: telemetry
42
+ 2024-01-02 13:43:42,021 INFO wandb-upload_0:8161 [upload_job.py:push():131] Uploaded file /tmp/tmpq1g9by67wandb/ve5qdbls-wandb-metadata.json
43
+ 2024-01-02 13:43:42,412 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/requirements.txt
44
+ 2024-01-02 13:43:42,413 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/wandb-metadata.json
45
+ 2024-01-02 13:43:42,413 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/output.log
46
+ 2024-01-02 13:43:43,992 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
47
+ 2024-01-02 13:43:48,993 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
48
+ 2024-01-02 13:43:53,994 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
49
+ 2024-01-02 13:43:56,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
50
+ 2024-01-02 13:43:56,691 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
51
+ 2024-01-02 13:43:56,691 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
52
+ 2024-01-02 13:43:59,738 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
53
+ 2024-01-02 13:44:04,739 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
54
+ 2024-01-02 13:44:09,749 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
55
+ 2024-01-02 13:44:10,481 INFO Thread-12 :8161 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/config.yaml
56
+ 2024-01-02 13:44:11,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
57
+ 2024-01-02 13:44:11,691 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
58
+ 2024-01-02 13:44:11,730 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
59
+ 2024-01-02 13:44:15,811 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
60
+ 2024-01-02 13:44:20,812 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
61
+ 2024-01-02 13:44:25,813 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
62
+ 2024-01-02 13:44:26,690 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
63
+ 2024-01-02 13:44:26,691 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
64
+ 2024-01-02 13:44:26,730 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
65
+ 2024-01-02 13:44:31,781 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
66
+ 2024-01-02 13:44:36,758 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: partial_history
67
+ 2024-01-02 13:44:36,760 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
68
+ 2024-01-02 13:44:36,761 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
69
+ 2024-01-02 13:44:36,761 DEBUG SenderThread:8161 [sender.py:send():382] send: metric
70
+ 2024-01-02 13:44:36,761 DEBUG SenderThread:8161 [sender.py:send():382] send: history
71
+ 2024-01-02 13:44:36,762 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: summary_record
72
+ 2024-01-02 13:44:36,770 INFO SenderThread:8161 [sender.py:_save_file():1392] saving file wandb-summary.json with policy end
73
+ 2024-01-02 13:44:37,549 INFO Thread-12 :8161 [dir_watcher.py:_on_file_created():271] file/dir created: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/wandb-summary.json
74
+ 2024-01-02 13:44:37,773 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
75
+ 2024-01-02 13:44:41,603 DEBUG SystemMonitor:8161 [system_monitor.py:_start():172] Starting system metrics aggregation loop
76
+ 2024-01-02 13:44:41,604 DEBUG SenderThread:8161 [sender.py:send():382] send: stats
77
+ 2024-01-02 13:44:41,698 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: stop_status
78
+ 2024-01-02 13:44:41,699 DEBUG SenderThread:8161 [sender.py:send_request():409] send_request: stop_status
79
+ 2024-01-02 13:44:41,704 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: internal_messages
80
+ 2024-01-02 13:44:43,762 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
81
+ 2024-01-02 13:44:44,858 INFO Thread-12 :8161 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/config.yaml
82
+ 2024-01-02 13:44:45,860 INFO Thread-12 :8161 [dir_watcher.py:_on_file_modified():288] file/dir modified: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/files/output.log
83
+ 2024-01-02 13:44:48,903 DEBUG HandlerThread:8161 [handler.py:handle_request():146] handle_request: status_report
wandb/run-20240102_134338-rjem4mwk/logs/debug.log ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-01-02 13:43:38,600 INFO MainThread:301 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
2
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Configure stats pid to 301
3
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
4
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Loading settings from /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/settings
5
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
6
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
8
+ 2024-01-02 13:43:38,601 INFO MainThread:301 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
9
+ 2024-01-02 13:43:38,602 INFO MainThread:301 [wandb_init.py:_log_setup():524] Logging user logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/logs/debug.log
10
+ 2024-01-02 13:43:38,602 INFO MainThread:301 [wandb_init.py:_log_setup():525] Logging internal logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Stock/wandb/run-20240102_134338-rjem4mwk/logs/debug-internal.log
11
+ 2024-01-02 13:43:38,603 INFO MainThread:301 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7b728cc2c340>
12
+ 2024-01-02 13:43:38,603 INFO MainThread:301 [wandb_init.py:init():564] calling init triggers
13
+ 2024-01-02 13:43:38,604 INFO MainThread:301 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
14
+ config: {}
15
+ 2024-01-02 13:43:38,604 INFO MainThread:301 [wandb_init.py:init():614] starting backend
16
+ 2024-01-02 13:43:38,604 INFO MainThread:301 [wandb_init.py:init():618] setting up manager
17
+ 2024-01-02 13:43:38,608 INFO MainThread:301 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-01-02 13:43:38,612 INFO MainThread:301 [wandb_init.py:init():624] backend started and connected
19
+ 2024-01-02 13:43:38,659 INFO MainThread:301 [wandb_run.py:_label_probe_notebook():1294] probe notebook
20
+ 2024-01-02 13:43:41,129 INFO MainThread:301 [wandb_init.py:init():716] updated telemetry
21
+ 2024-01-02 13:43:41,139 INFO MainThread:301 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
22
+ 2024-01-02 13:43:41,418 INFO MainThread:301 [wandb_run.py:_on_init():2254] communicating current version
23
+ 2024-01-02 13:43:41,575 INFO MainThread:301 [wandb_run.py:_on_init():2263] got version response
24
+ 2024-01-02 13:43:41,575 INFO MainThread:301 [wandb_init.py:init():800] starting run threads in backend
25
+ 2024-01-02 13:43:41,690 INFO MainThread:301 [wandb_run.py:_console_start():2233] atexit reg
26
+ 2024-01-02 13:43:41,690 INFO MainThread:301 [wandb_run.py:_redirect():2088] redirect: wrap_raw
27
+ 2024-01-02 13:43:41,691 INFO MainThread:301 [wandb_run.py:_redirect():2153] Wrapping output streams.
28
+ 2024-01-02 13:43:41,691 INFO MainThread:301 [wandb_run.py:_redirect():2178] Redirects installed.
29
+ 2024-01-02 13:43:41,693 INFO MainThread:301 [wandb_init.py:init():841] run started, returning control to user process
30
+ 2024-01-02 13:43:41,699 INFO MainThread:301 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, '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': False, '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': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.37.0.dev0', 'model_type': 'mistral', '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/Mistral-7B-Finetuning-Stock', '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': 60, '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/Mistral-7B-Finetuning-Stock/runs/Jan02_13-42-45_915b2a0951c7', '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/Mistral-7B-Finetuning-Stock', '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-20240102_134338-rjem4mwk/run-rjem4mwk.wandb ADDED
File without changes