Training in progress, step 20

adapter_config.json

@@ -1,9 +1,6 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": {
-    "base_model_class": "BloomForCausalLM",
-    "parent_library": "transformers.models.bloom.modeling_bloom"
-  },
+  "auto_mapping": null,
   "base_model_name_or_path": "bigscience/bloomz-1b1",
   "bias": "none",
   "fan_in_fan_out": false,
@@ -26,7 +23,7 @@
     "query_key_valuelm_head",
     "word_embeddings"
   ],
-  "task_type": null,
+  "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270f7a985c38ef87d3b0c62d407b8c8e1e8a69c4b0b3fcff9cbdaefb08b99e6e
+oid sha256:3ea77a2400c32cfb7cf6845fdbd212870169c65e267554bf3ddf8bf631948cdc
 size 8077608

runs/Apr12_07-33-49_e5a48bec8248/events.out.tfevents.1712907230.e5a48bec8248.174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6636275300a1b9bf7a83951f2cceefe8a6f9b4f3df60c1573079e7b0469582b
+size 5486

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:439f3807656f67fbb80a340aba983b1e64e3589ce5602b15e2abaffb2bc57416
+oid sha256:83256b55088d45d0ebeda1319a91e9b247c70b5f4d82cb04a018aa4a684554bc
 size 4984

wandb/debug-internal.log

@@ -113,3 +113,166 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:28:23,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 07:28:23,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
 2024-04-12 07:28:24,273 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:26,760 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: pause
+2024-04-12 07:28:26,760 INFO    HandlerThread:216 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-04-12 07:28:26,760 INFO    HandlerThread:216 [system_monitor.py:finish():203] Stopping system monitor
+2024-04-12 07:28:26,761 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined cpu monitor
+2024-04-12 07:28:26,761 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined disk monitor
+2024-04-12 07:28:26,761 DEBUG   SystemMonitor:216 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-12 07:28:26,761 DEBUG   SystemMonitor:216 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-04-12 07:28:26,762 DEBUG   SystemMonitor:216 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined gpu monitor
+2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined memory monitor
+2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined network monitor
+2024-04-12 07:28:26,775 DEBUG   SenderThread:216 [sender.py:send():379] send: stats
+2024-04-12 07:28:29,776 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:34,777 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:38,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:28:38,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:28:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:28:40,261 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:41,053 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:28:45,363 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:50,364 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:53,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:28:53,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:28:53,234 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:28:56,263 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:01,264 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:06,266 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:08,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:08,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:08,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:12,239 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:17,240 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:22,241 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:23,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:23,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:23,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:27,289 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:32,290 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:37,291 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:38,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:38,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:38,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:42,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:47,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:52,327 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:53,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:53,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:53,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:58,280 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:03,281 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:08,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:08,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:08,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:09,269 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:14,270 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:19,271 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:23,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:23,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:23,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:24,322 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:29,323 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:34,324 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:38,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:38,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:38,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:39,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:44,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:49,327 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:53,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:53,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:53,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:55,310 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:00,311 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:05,312 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:08,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:08,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:08,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:11,254 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:16,255 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:21,256 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:23,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:23,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:23,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:26,273 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:31,274 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:36,275 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:38,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:38,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:38,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:41,323 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:46,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:51,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:53,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:53,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:53,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:57,277 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:02,278 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:07,279 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:08,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:08,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:08,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:12,341 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:17,342 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:22,343 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:23,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:23,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:23,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:28,314 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:33,315 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:38,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:38,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:38,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:39,296 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:44,297 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:49,299 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:53,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:53,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:53,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:55,259 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:00,260 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:05,261 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:08,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:08,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:08,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:10,292 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:15,293 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:20,294 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:23,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:23,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:23,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:26,254 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:31,255 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:36,256 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:38,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:38,238 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:41,304 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:46,269 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: resume
+2024-04-12 07:33:46,269 INFO    HandlerThread:216 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-04-12 07:33:46,269 INFO    HandlerThread:216 [system_monitor.py:start():194] Starting system monitor
+2024-04-12 07:33:46,269 INFO    SystemMonitor:216 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-12 07:33:46,270 INFO    SystemMonitor:216 [interfaces.py:start():190] Started cpu monitoring
+2024-04-12 07:33:46,271 INFO    SystemMonitor:216 [interfaces.py:start():190] Started disk monitoring
+2024-04-12 07:33:46,271 INFO    SystemMonitor:216 [interfaces.py:start():190] Started gpu monitoring
+2024-04-12 07:33:46,272 INFO    SystemMonitor:216 [interfaces.py:start():190] Started memory monitoring
+2024-04-12 07:33:46,273 INFO    SystemMonitor:216 [interfaces.py:start():190] Started network monitoring
+2024-04-12 07:33:46,304 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:50,616 DEBUG   SenderThread:216 [sender.py:send():379] send: config
+2024-04-12 07:33:50,617 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
+2024-04-12 07:33:50,617 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
+2024-04-12 07:33:50,617 WARNING SenderThread:216 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-12 07:33:51,634 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:52,173 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:33:52,173 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
+2024-04-12 07:33:53,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:53,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:53,200 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:57,222 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:33:57,224 DEBUG   SenderThread:216 [sender.py:send():379] send: history
+2024-04-12 07:33:57,224 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:33:57,224 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:57,225 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:33:58,175 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json

wandb/debug.log

@@ -29,3 +29,7 @@ config: {}
 2024-04-12 07:27:53,194 INFO    MainThread:174 [wandb_run.py:_redirect():2268] Redirects installed.
 2024-04-12 07:27:53,195 INFO    MainThread:174 [wandb_init.py:init():848] run started, returning control to user process
 2024-04-12 07:27:53,201 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 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': '/kaggle/working/runs/Apr12_07-27-33_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': 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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-04-12 07:28:26,759 INFO    MainThread:174 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-04-12 07:28:26,759 INFO    MainThread:174 [wandb_init.py:_pause_backend():438] pausing backend
+2024-04-12 07:33:46,268 INFO    MainThread:174 [wandb_init.py:_resume_backend():443] resuming backend
+2024-04-12 07:33:50,610 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 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': '/kaggle/working/runs/Apr12_07-33-49_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': 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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}

wandb/run-20240412_072736-gyl3aena/files/config.yaml

@@ -44,6 +44,7 @@ _wandb:
       3:
       - 7
       - 23
+      - 62
       4: 3.10.13
       5: 0.16.5
       6: 4.39.3
@@ -415,7 +416,7 @@ log_on_each_node:
   value: true
 logging_dir:
   desc: null
-  value: /kaggle/working/runs/Apr12_07-27-33_e5a48bec8248
+  value: /kaggle/working/runs/Apr12_07-33-49_e5a48bec8248
 logging_strategy:
   desc: null
   value: steps

wandb/run-20240412_072736-gyl3aena/files/output.log

@@ -2,4 +2,10 @@
   warnings.warn(
 /opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
   warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+trainable params: 2,019,328 || all params: 1,067,333,632 || trainable%: 0.18919370096266205
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:432: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
 /opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.

wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 4.8386, "train/grad_norm": 73.25434112548828, "train/learning_rate": 0.0, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1712906893.8035388, "_runtime": 37.171459913253784, "_step": 3, "train_runtime": 39.0078, "train_samples_per_second": 3.076, "train_steps_per_second": 1.538, "total_flos": 19812939669504.0, "train_loss": 4.6811678568522135}
+{"train/loss": 4.6745, "train/grad_norm": 87.1609115600586, "train/learning_rate": 2.341780598043574e-05, "train/epoch": 0.0, "train/global_step": 20, "_timestamp": 1712907237.222082, "_runtime": 380.59000301361084, "_step": 4, "train_runtime": 39.0078, "train_samples_per_second": 3.076, "train_steps_per_second": 1.538, "total_flos": 19812939669504.0, "train_loss": 4.6811678568522135}

wandb/run-20240412_072736-gyl3aena/logs/debug-internal.log

@@ -113,3 +113,166 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:28:23,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 07:28:23,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
 2024-04-12 07:28:24,273 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:26,760 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: pause
+2024-04-12 07:28:26,760 INFO    HandlerThread:216 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-04-12 07:28:26,760 INFO    HandlerThread:216 [system_monitor.py:finish():203] Stopping system monitor
+2024-04-12 07:28:26,761 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined cpu monitor
+2024-04-12 07:28:26,761 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined disk monitor
+2024-04-12 07:28:26,761 DEBUG   SystemMonitor:216 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-12 07:28:26,761 DEBUG   SystemMonitor:216 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-04-12 07:28:26,762 DEBUG   SystemMonitor:216 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined gpu monitor
+2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined memory monitor
+2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined network monitor
+2024-04-12 07:28:26,775 DEBUG   SenderThread:216 [sender.py:send():379] send: stats
+2024-04-12 07:28:29,776 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:34,777 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:38,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:28:38,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:28:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:28:40,261 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:41,053 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:28:45,363 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:50,364 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:53,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:28:53,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:28:53,234 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:28:56,263 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:01,264 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:06,266 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:08,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:08,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:08,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:12,239 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:17,240 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:22,241 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:23,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:23,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:23,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:27,289 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:32,290 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:37,291 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:38,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:38,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:38,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:42,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:47,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:52,327 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:29:53,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:29:53,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:29:53,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:29:58,280 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:03,281 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:08,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:08,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:08,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:09,269 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:14,270 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:19,271 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:23,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:23,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:23,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:24,322 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:29,323 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:34,324 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:38,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:38,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:38,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:39,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:44,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:49,327 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:30:53,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:30:53,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:30:53,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:30:55,310 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:00,311 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:05,312 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:08,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:08,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:08,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:11,254 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:16,255 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:21,256 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:23,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:23,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:23,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:26,273 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:31,274 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:36,275 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:38,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:38,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:38,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:41,323 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:46,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:51,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:31:53,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:31:53,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:31:53,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:31:57,277 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:02,278 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:07,279 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:08,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:08,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:08,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:12,341 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:17,342 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:22,343 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:23,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:23,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:23,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:28,314 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:33,315 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:38,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:38,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:38,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:39,296 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:44,297 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:49,299 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:32:53,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:32:53,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:32:53,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:32:55,259 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:00,260 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:05,261 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:08,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:08,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:08,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:10,292 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:15,293 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:20,294 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:23,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:23,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:23,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:26,254 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:31,255 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:36,256 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:38,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:38,238 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:41,304 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:46,269 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: resume
+2024-04-12 07:33:46,269 INFO    HandlerThread:216 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-04-12 07:33:46,269 INFO    HandlerThread:216 [system_monitor.py:start():194] Starting system monitor
+2024-04-12 07:33:46,269 INFO    SystemMonitor:216 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-12 07:33:46,270 INFO    SystemMonitor:216 [interfaces.py:start():190] Started cpu monitoring
+2024-04-12 07:33:46,271 INFO    SystemMonitor:216 [interfaces.py:start():190] Started disk monitoring
+2024-04-12 07:33:46,271 INFO    SystemMonitor:216 [interfaces.py:start():190] Started gpu monitoring
+2024-04-12 07:33:46,272 INFO    SystemMonitor:216 [interfaces.py:start():190] Started memory monitoring
+2024-04-12 07:33:46,273 INFO    SystemMonitor:216 [interfaces.py:start():190] Started network monitoring
+2024-04-12 07:33:46,304 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:50,616 DEBUG   SenderThread:216 [sender.py:send():379] send: config
+2024-04-12 07:33:50,617 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
+2024-04-12 07:33:50,617 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
+2024-04-12 07:33:50,617 WARNING SenderThread:216 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-12 07:33:51,634 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:52,173 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:33:52,173 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
+2024-04-12 07:33:53,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:33:53,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:33:53,200 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:33:57,222 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:33:57,224 DEBUG   SenderThread:216 [sender.py:send():379] send: history
+2024-04-12 07:33:57,224 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:33:57,224 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:33:57,225 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:33:58,175 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json

wandb/run-20240412_072736-gyl3aena/logs/debug.log

@@ -29,3 +29,7 @@ config: {}
 2024-04-12 07:27:53,194 INFO    MainThread:174 [wandb_run.py:_redirect():2268] Redirects installed.
 2024-04-12 07:27:53,195 INFO    MainThread:174 [wandb_init.py:init():848] run started, returning control to user process
 2024-04-12 07:27:53,201 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 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': '/kaggle/working/runs/Apr12_07-27-33_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': 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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-04-12 07:28:26,759 INFO    MainThread:174 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-04-12 07:28:26,759 INFO    MainThread:174 [wandb_init.py:_pause_backend():438] pausing backend
+2024-04-12 07:33:46,268 INFO    MainThread:174 [wandb_init.py:_resume_backend():443] resuming backend
+2024-04-12 07:33:50,610 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 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': '/kaggle/working/runs/Apr12_07-33-49_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': 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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}