Hugging Face's logo

csujeong
/
Falcon-7B-Fintued-Finance-Stock-E

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
csujeong commited on
Commit
9f0bd2f
•
1 Parent(s): 46f8ed8

End of training

Browse files
Files changed (5) hide show
  1. README.md +59 -0
  2. wandb/debug-internal.log +86 -0
  3. wandb/debug.log +3 -0
  4. wandb/run-20231225_023520-367ycxh7/logs/debug-internal.log +86 -0
  5. wandb/run-20231225_023520-367ycxh7/logs/debug.log +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: tiiuae/falcon-7b
9
+ model-index:
10
+ - name: Falcon-7B-Fintued-Finance-Stock-E
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Falcon-7B-Fintued-Finance-Stock-E
18
+
19
+ This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 4
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.03
47
+ - training_steps: 60
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.7.2.dev0
56
+ - Transformers 4.36.2
57
+ - Pytorch 2.1.0+cu121
58
+ - Datasets 2.16.0
59
+ - Tokenizers 0.15.0
wandb/debug-internal.log CHANGED
@@ -237,3 +237,89 @@
237
  2023-12-25 02:41:08,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
238
  2023-12-25 02:41:08,217 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
239
  2023-12-25 02:41:12,287 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
237
  2023-12-25 02:41:08,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
238
  2023-12-25 02:41:08,217 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
239
  2023-12-25 02:41:12,287 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
240
+ 2023-12-25 02:41:16,633 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: pause
241
+ 2023-12-25 02:41:16,634 INFO HandlerThread:5727 [handler.py:handle_request_pause():705] stopping system metrics thread
242
+ 2023-12-25 02:41:16,634 INFO HandlerThread:5727 [system_monitor.py:finish():203] Stopping system monitor
243
+ 2023-12-25 02:41:16,635 DEBUG SystemMonitor:5727 [system_monitor.py:_start():179] Finished system metrics aggregation loop
244
+ 2023-12-25 02:41:16,637 DEBUG SystemMonitor:5727 [system_monitor.py:_start():183] Publishing last batch of metrics
245
+ 2023-12-25 02:41:16,637 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined cpu monitor
246
+ 2023-12-25 02:41:16,649 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined disk monitor
247
+ 2023-12-25 02:41:16,652 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined gpu monitor
248
+ 2023-12-25 02:41:16,653 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined memory monitor
249
+ 2023-12-25 02:41:16,653 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined network monitor
250
+ 2023-12-25 02:41:16,657 DEBUG SenderThread:5727 [sender.py:send():382] send: stats
251
+ 2023-12-25 02:41:17,658 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
252
+ 2023-12-25 02:41:22,659 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
253
+ 2023-12-25 02:41:23,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
254
+ 2023-12-25 02:41:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
255
+ 2023-12-25 02:41:23,217 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
256
+ 2023-12-25 02:41:28,318 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
257
+ 2023-12-25 02:41:33,319 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
258
+ 2023-12-25 02:41:38,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
259
+ 2023-12-25 02:41:38,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
260
+ 2023-12-25 02:41:38,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
261
+ 2023-12-25 02:41:39,299 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
262
+ 2023-12-25 02:41:44,299 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
263
+ 2023-12-25 02:41:49,300 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
264
+ 2023-12-25 02:41:53,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
265
+ 2023-12-25 02:41:53,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
266
+ 2023-12-25 02:41:53,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
267
+ 2023-12-25 02:41:54,396 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
268
+ 2023-12-25 02:41:59,397 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
269
+ 2023-12-25 02:42:04,397 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
270
+ 2023-12-25 02:42:08,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
271
+ 2023-12-25 02:42:08,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
272
+ 2023-12-25 02:42:08,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
273
+ 2023-12-25 02:42:10,355 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
274
+ 2023-12-25 02:42:15,356 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
275
+ 2023-12-25 02:42:20,357 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
276
+ 2023-12-25 02:42:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
277
+ 2023-12-25 02:42:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
278
+ 2023-12-25 02:42:23,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
279
+ 2023-12-25 02:42:25,361 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
280
+ 2023-12-25 02:42:30,361 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
281
+ 2023-12-25 02:42:35,362 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
282
+ 2023-12-25 02:42:38,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
283
+ 2023-12-25 02:42:38,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
284
+ 2023-12-25 02:42:38,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
285
+ 2023-12-25 02:42:41,323 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
286
+ 2023-12-25 02:42:46,324 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
287
+ 2023-12-25 02:42:51,325 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
288
+ 2023-12-25 02:42:53,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
289
+ 2023-12-25 02:42:53,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
290
+ 2023-12-25 02:42:53,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
291
+ 2023-12-25 02:42:57,319 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
292
+ 2023-12-25 02:43:02,320 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
293
+ 2023-12-25 02:43:07,320 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
294
+ 2023-12-25 02:43:08,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
295
+ 2023-12-25 02:43:08,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
296
+ 2023-12-25 02:43:08,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
297
+ 2023-12-25 02:43:12,345 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
298
+ 2023-12-25 02:43:17,346 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
299
+ 2023-12-25 02:43:22,347 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
300
+ 2023-12-25 02:43:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
301
+ 2023-12-25 02:43:23,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
302
+ 2023-12-25 02:43:23,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
303
+ 2023-12-25 02:43:27,369 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
304
+ 2023-12-25 02:43:32,370 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
305
+ 2023-12-25 02:43:37,371 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
306
+ 2023-12-25 02:43:38,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
307
+ 2023-12-25 02:43:38,219 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
308
+ 2023-12-25 02:43:38,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
309
+ 2023-12-25 02:43:43,353 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
310
+ 2023-12-25 02:43:48,353 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
311
+ 2023-12-25 02:43:53,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
312
+ 2023-12-25 02:43:53,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
313
+ 2023-12-25 02:43:53,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
314
+ 2023-12-25 02:43:54,335 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
315
+ 2023-12-25 02:43:59,336 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
316
+ 2023-12-25 02:44:02,973 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: resume
317
+ 2023-12-25 02:44:02,975 INFO HandlerThread:5727 [handler.py:handle_request_resume():696] starting system metrics thread
318
+ 2023-12-25 02:44:02,975 INFO HandlerThread:5727 [system_monitor.py:start():194] Starting system monitor
319
+ 2023-12-25 02:44:02,979 INFO SystemMonitor:5727 [system_monitor.py:_start():158] Starting system asset monitoring threads
320
+ 2023-12-25 02:44:02,980 INFO SystemMonitor:5727 [interfaces.py:start():190] Started cpu monitoring
321
+ 2023-12-25 02:44:02,981 INFO SystemMonitor:5727 [interfaces.py:start():190] Started disk monitoring
322
+ 2023-12-25 02:44:02,982 INFO SystemMonitor:5727 [interfaces.py:start():190] Started gpu monitoring
323
+ 2023-12-25 02:44:02,988 INFO SystemMonitor:5727 [interfaces.py:start():190] Started memory monitoring
324
+ 2023-12-25 02:44:02,989 INFO SystemMonitor:5727 [interfaces.py:start():190] Started network monitoring
325
+ 2023-12-25 02:44:04,337 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
wandb/debug.log CHANGED
@@ -28,3 +28,6 @@ config: {}
28
  2023-12-25 02:35:23,199 INFO MainThread:239 [wandb_run.py:_redirect():2178] Redirects installed.
29
  2023-12-25 02:35:23,203 INFO MainThread:239 [wandb_init.py:init():841] run started, returning control to user process
30
  2023-12-25 02:35:23,222 INFO MainThread:239 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 65024, 'hidden_size': 4544, 'num_hidden_layers': 32, 'num_attention_heads': 71, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 11, 'eos_token_id': 11, 'num_kv_heads': 71, 'alibi': False, 'new_decoder_architecture': False, 'multi_query': True, 'parallel_attn': True, 'bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['FalconForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'tiiuae/falcon-7b', 'transformers_version': '4.36.2', 'apply_residual_connection_post_layernorm': False, 'auto_map': {'AutoConfig': 'tiiuae/falcon-7b--configuration_falcon.FalconConfig', 'AutoModel': 'tiiuae/falcon-7b--modeling_falcon.FalconModel', 'AutoModelForSequenceClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification', 'AutoModelForTokenClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification', 'AutoModelForQuestionAnswering': 'tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering', 'AutoModelForCausalLM': 'tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM'}, 'model_type': 'falcon', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', 'load_in_8bit': False, 'load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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/Falcon-7B-Fintued-Finance-Stock-E/runs/Dec25_02-34-12_e0dc55e75a0e', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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}
 
 
 
 
28
  2023-12-25 02:35:23,199 INFO MainThread:239 [wandb_run.py:_redirect():2178] Redirects installed.
29
  2023-12-25 02:35:23,203 INFO MainThread:239 [wandb_init.py:init():841] run started, returning control to user process
30
  2023-12-25 02:35:23,222 INFO MainThread:239 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 65024, 'hidden_size': 4544, 'num_hidden_layers': 32, 'num_attention_heads': 71, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 11, 'eos_token_id': 11, 'num_kv_heads': 71, 'alibi': False, 'new_decoder_architecture': False, 'multi_query': True, 'parallel_attn': True, 'bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['FalconForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'tiiuae/falcon-7b', 'transformers_version': '4.36.2', 'apply_residual_connection_post_layernorm': False, 'auto_map': {'AutoConfig': 'tiiuae/falcon-7b--configuration_falcon.FalconConfig', 'AutoModel': 'tiiuae/falcon-7b--modeling_falcon.FalconModel', 'AutoModelForSequenceClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification', 'AutoModelForTokenClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification', 'AutoModelForQuestionAnswering': 'tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering', 'AutoModelForCausalLM': 'tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM'}, 'model_type': 'falcon', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', 'load_in_8bit': False, 'load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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/Falcon-7B-Fintued-Finance-Stock-E/runs/Dec25_02-34-12_e0dc55e75a0e', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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}
31
+ 2023-12-25 02:41:16,632 INFO MainThread:239 [jupyter.py:save_ipynb():373] not saving jupyter notebook
32
+ 2023-12-25 02:41:16,632 INFO MainThread:239 [wandb_init.py:_pause_backend():435] pausing backend
33
+ 2023-12-25 02:44:02,972 INFO MainThread:239 [wandb_init.py:_resume_backend():440] resuming backend
wandb/run-20231225_023520-367ycxh7/logs/debug-internal.log CHANGED
@@ -237,3 +237,89 @@
237
  2023-12-25 02:41:08,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
238
  2023-12-25 02:41:08,217 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
239
  2023-12-25 02:41:12,287 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
237
  2023-12-25 02:41:08,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
238
  2023-12-25 02:41:08,217 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
239
  2023-12-25 02:41:12,287 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
240
+ 2023-12-25 02:41:16,633 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: pause
241
+ 2023-12-25 02:41:16,634 INFO HandlerThread:5727 [handler.py:handle_request_pause():705] stopping system metrics thread
242
+ 2023-12-25 02:41:16,634 INFO HandlerThread:5727 [system_monitor.py:finish():203] Stopping system monitor
243
+ 2023-12-25 02:41:16,635 DEBUG SystemMonitor:5727 [system_monitor.py:_start():179] Finished system metrics aggregation loop
244
+ 2023-12-25 02:41:16,637 DEBUG SystemMonitor:5727 [system_monitor.py:_start():183] Publishing last batch of metrics
245
+ 2023-12-25 02:41:16,637 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined cpu monitor
246
+ 2023-12-25 02:41:16,649 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined disk monitor
247
+ 2023-12-25 02:41:16,652 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined gpu monitor
248
+ 2023-12-25 02:41:16,653 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined memory monitor
249
+ 2023-12-25 02:41:16,653 INFO HandlerThread:5727 [interfaces.py:finish():202] Joined network monitor
250
+ 2023-12-25 02:41:16,657 DEBUG SenderThread:5727 [sender.py:send():382] send: stats
251
+ 2023-12-25 02:41:17,658 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
252
+ 2023-12-25 02:41:22,659 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
253
+ 2023-12-25 02:41:23,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
254
+ 2023-12-25 02:41:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
255
+ 2023-12-25 02:41:23,217 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
256
+ 2023-12-25 02:41:28,318 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
257
+ 2023-12-25 02:41:33,319 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
258
+ 2023-12-25 02:41:38,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
259
+ 2023-12-25 02:41:38,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
260
+ 2023-12-25 02:41:38,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
261
+ 2023-12-25 02:41:39,299 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
262
+ 2023-12-25 02:41:44,299 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
263
+ 2023-12-25 02:41:49,300 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
264
+ 2023-12-25 02:41:53,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
265
+ 2023-12-25 02:41:53,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
266
+ 2023-12-25 02:41:53,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
267
+ 2023-12-25 02:41:54,396 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
268
+ 2023-12-25 02:41:59,397 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
269
+ 2023-12-25 02:42:04,397 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
270
+ 2023-12-25 02:42:08,216 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
271
+ 2023-12-25 02:42:08,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
272
+ 2023-12-25 02:42:08,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
273
+ 2023-12-25 02:42:10,355 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
274
+ 2023-12-25 02:42:15,356 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
275
+ 2023-12-25 02:42:20,357 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
276
+ 2023-12-25 02:42:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
277
+ 2023-12-25 02:42:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
278
+ 2023-12-25 02:42:23,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
279
+ 2023-12-25 02:42:25,361 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
280
+ 2023-12-25 02:42:30,361 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
281
+ 2023-12-25 02:42:35,362 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
282
+ 2023-12-25 02:42:38,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
283
+ 2023-12-25 02:42:38,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
284
+ 2023-12-25 02:42:38,218 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
285
+ 2023-12-25 02:42:41,323 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
286
+ 2023-12-25 02:42:46,324 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
287
+ 2023-12-25 02:42:51,325 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
288
+ 2023-12-25 02:42:53,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
289
+ 2023-12-25 02:42:53,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
290
+ 2023-12-25 02:42:53,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
291
+ 2023-12-25 02:42:57,319 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
292
+ 2023-12-25 02:43:02,320 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
293
+ 2023-12-25 02:43:07,320 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
294
+ 2023-12-25 02:43:08,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
295
+ 2023-12-25 02:43:08,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
296
+ 2023-12-25 02:43:08,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
297
+ 2023-12-25 02:43:12,345 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
298
+ 2023-12-25 02:43:17,346 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
299
+ 2023-12-25 02:43:22,347 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
300
+ 2023-12-25 02:43:23,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
301
+ 2023-12-25 02:43:23,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
302
+ 2023-12-25 02:43:23,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
303
+ 2023-12-25 02:43:27,369 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
304
+ 2023-12-25 02:43:32,370 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
305
+ 2023-12-25 02:43:37,371 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
306
+ 2023-12-25 02:43:38,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
307
+ 2023-12-25 02:43:38,219 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
308
+ 2023-12-25 02:43:38,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
309
+ 2023-12-25 02:43:43,353 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
310
+ 2023-12-25 02:43:48,353 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
311
+ 2023-12-25 02:43:53,217 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: internal_messages
312
+ 2023-12-25 02:43:53,218 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: stop_status
313
+ 2023-12-25 02:43:53,219 DEBUG SenderThread:5727 [sender.py:send_request():409] send_request: stop_status
314
+ 2023-12-25 02:43:54,335 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
315
+ 2023-12-25 02:43:59,336 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
316
+ 2023-12-25 02:44:02,973 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: resume
317
+ 2023-12-25 02:44:02,975 INFO HandlerThread:5727 [handler.py:handle_request_resume():696] starting system metrics thread
318
+ 2023-12-25 02:44:02,975 INFO HandlerThread:5727 [system_monitor.py:start():194] Starting system monitor
319
+ 2023-12-25 02:44:02,979 INFO SystemMonitor:5727 [system_monitor.py:_start():158] Starting system asset monitoring threads
320
+ 2023-12-25 02:44:02,980 INFO SystemMonitor:5727 [interfaces.py:start():190] Started cpu monitoring
321
+ 2023-12-25 02:44:02,981 INFO SystemMonitor:5727 [interfaces.py:start():190] Started disk monitoring
322
+ 2023-12-25 02:44:02,982 INFO SystemMonitor:5727 [interfaces.py:start():190] Started gpu monitoring
323
+ 2023-12-25 02:44:02,988 INFO SystemMonitor:5727 [interfaces.py:start():190] Started memory monitoring
324
+ 2023-12-25 02:44:02,989 INFO SystemMonitor:5727 [interfaces.py:start():190] Started network monitoring
325
+ 2023-12-25 02:44:04,337 DEBUG HandlerThread:5727 [handler.py:handle_request():146] handle_request: status_report
wandb/run-20231225_023520-367ycxh7/logs/debug.log CHANGED
@@ -28,3 +28,6 @@ config: {}
28
  2023-12-25 02:35:23,199 INFO MainThread:239 [wandb_run.py:_redirect():2178] Redirects installed.
29
  2023-12-25 02:35:23,203 INFO MainThread:239 [wandb_init.py:init():841] run started, returning control to user process
30
  2023-12-25 02:35:23,222 INFO MainThread:239 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 65024, 'hidden_size': 4544, 'num_hidden_layers': 32, 'num_attention_heads': 71, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 11, 'eos_token_id': 11, 'num_kv_heads': 71, 'alibi': False, 'new_decoder_architecture': False, 'multi_query': True, 'parallel_attn': True, 'bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['FalconForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'tiiuae/falcon-7b', 'transformers_version': '4.36.2', 'apply_residual_connection_post_layernorm': False, 'auto_map': {'AutoConfig': 'tiiuae/falcon-7b--configuration_falcon.FalconConfig', 'AutoModel': 'tiiuae/falcon-7b--modeling_falcon.FalconModel', 'AutoModelForSequenceClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification', 'AutoModelForTokenClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification', 'AutoModelForQuestionAnswering': 'tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering', 'AutoModelForCausalLM': 'tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM'}, 'model_type': 'falcon', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', 'load_in_8bit': False, 'load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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/Falcon-7B-Fintued-Finance-Stock-E/runs/Dec25_02-34-12_e0dc55e75a0e', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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}
 
 
 
 
28
  2023-12-25 02:35:23,199 INFO MainThread:239 [wandb_run.py:_redirect():2178] Redirects installed.
29
  2023-12-25 02:35:23,203 INFO MainThread:239 [wandb_init.py:init():841] run started, returning control to user process
30
  2023-12-25 02:35:23,222 INFO MainThread:239 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 65024, 'hidden_size': 4544, 'num_hidden_layers': 32, 'num_attention_heads': 71, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 11, 'eos_token_id': 11, 'num_kv_heads': 71, 'alibi': False, 'new_decoder_architecture': False, 'multi_query': True, 'parallel_attn': True, 'bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['FalconForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'tiiuae/falcon-7b', 'transformers_version': '4.36.2', 'apply_residual_connection_post_layernorm': False, 'auto_map': {'AutoConfig': 'tiiuae/falcon-7b--configuration_falcon.FalconConfig', 'AutoModel': 'tiiuae/falcon-7b--modeling_falcon.FalconModel', 'AutoModelForSequenceClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification', 'AutoModelForTokenClassification': 'tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification', 'AutoModelForQuestionAnswering': 'tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering', 'AutoModelForCausalLM': 'tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM'}, 'model_type': 'falcon', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', 'load_in_8bit': False, 'load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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/Falcon-7B-Fintued-Finance-Stock-E/runs/Dec25_02-34-12_e0dc55e75a0e', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Falcon-7B-Fintued-Finance-Stock-E', '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}
31
+ 2023-12-25 02:41:16,632 INFO MainThread:239 [jupyter.py:save_ipynb():373] not saving jupyter notebook
32
+ 2023-12-25 02:41:16,632 INFO MainThread:239 [wandb_init.py:_pause_backend():435] pausing backend
33
+ 2023-12-25 02:44:02,972 INFO MainThread:239 [wandb_init.py:_resume_backend():440] resuming backend