Upload W&B logs

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 wandb_logs/run-20251122_161333-76f9jnsn/run-76f9jnsn.wandb filter=lfs diff=lfs merge=lfs -text
+wandb_logs/run-20251122_173629-7f2wzkw5/run-7f2wzkw5.wandb filter=lfs diff=lfs merge=lfs -text

wandb_logs/debug-internal.log

@@ -1,12 +1,12 @@
-{"time":"2025-11-22T16:13:34.153809441Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
-{"time":"2025-11-22T16:13:34.340337859Z","level":"INFO","msg":"stream: created new stream","id":"76f9jnsn"}
-{"time":"2025-11-22T16:13:34.340404845Z","level":"INFO","msg":"handler: started","stream_id":"76f9jnsn"}
-{"time":"2025-11-22T16:13:34.34065159Z","level":"INFO","msg":"stream: started","id":"76f9jnsn"}
-{"time":"2025-11-22T16:13:34.340661345Z","level":"INFO","msg":"writer: started","stream_id":"76f9jnsn"}
-{"time":"2025-11-22T16:13:34.340682698Z","level":"INFO","msg":"sender: started","stream_id":"76f9jnsn"}
-{"time":"2025-11-22T16:18:09.125900363Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
-{"time":"2025-11-22T16:18:09.277753442Z","level":"INFO","msg":"handler: operation stats","stats":{}}
-{"time":"2025-11-22T16:18:09.284937721Z","level":"INFO","msg":"stream: closing","id":"76f9jnsn"}
-{"time":"2025-11-22T16:18:09.284962535Z","level":"INFO","msg":"handler: closed","stream_id":"76f9jnsn"}
-{"time":"2025-11-22T16:18:09.285025518Z","level":"INFO","msg":"sender: closed","stream_id":"76f9jnsn"}
-{"time":"2025-11-22T16:18:09.285038449Z","level":"INFO","msg":"stream: closed","id":"76f9jnsn"}
+{"time":"2025-11-22T17:36:30.309809744Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
+{"time":"2025-11-22T17:36:30.658933282Z","level":"INFO","msg":"stream: created new stream","id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659033035Z","level":"INFO","msg":"handler: started","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659231232Z","level":"INFO","msg":"stream: started","id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659288352Z","level":"INFO","msg":"writer: started","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659315281Z","level":"INFO","msg":"sender: started","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.479276173Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-11-22T17:43:28.793500251Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-11-22T17:43:28.80038483Z","level":"INFO","msg":"stream: closing","id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.800412693Z","level":"INFO","msg":"handler: closed","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.800474018Z","level":"INFO","msg":"sender: closed","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.800494226Z","level":"INFO","msg":"stream: closed","id":"7f2wzkw5"}

wandb_logs/debug.log

@@ -1,29 +1,29 @@
-2025-11-22 16:13:33,411 INFO    MainThread:1796 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
-2025-11-22 16:13:33,411 INFO    MainThread:1796 [wandb_setup.py:_flush():80] Configure stats pid to 1796
-2025-11-22 16:13:33,411 INFO    MainThread:1796 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
-2025-11-22 16:13:33,411 INFO    MainThread:1796 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
-2025-11-22 16:13:33,411 INFO    MainThread:1796 [wandb_setup.py:_flush():80] Loading settings from environment variables
-2025-11-22 16:13:33,411 INFO    MainThread:1796 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_161333-76f9jnsn/logs/debug.log
-2025-11-22 16:13:33,412 INFO    MainThread:1796 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_161333-76f9jnsn/logs/debug-internal.log
-2025-11-22 16:13:33,412 INFO    MainThread:1796 [wandb_init.py:init():840] calling init triggers
-2025-11-22 16:13:33,412 INFO    MainThread:1796 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Configure stats pid to 1459
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_173629-7f2wzkw5/logs/debug.log
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_173629-7f2wzkw5/logs/debug-internal.log
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:init():840] calling init triggers
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
 config: {'model': 'bert-base-multilingual-cased', 'train_file': 'synthetic_data_gen/data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
-2025-11-22 16:13:33,412 INFO    MainThread:1796 [wandb_init.py:init():888] starting backend
-2025-11-22 16:13:34,135 INFO    MainThread:1796 [wandb_init.py:init():891] sending inform_init request
-2025-11-22 16:13:34,146 INFO    MainThread:1796 [wandb_init.py:init():899] backend started and connected
-2025-11-22 16:13:34,149 INFO    MainThread:1796 [wandb_init.py:init():969] updated telemetry
-2025-11-22 16:13:34,155 INFO    MainThread:1796 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
-2025-11-22 16:13:34,639 INFO    MainThread:1796 [wandb_init.py:init():1040] starting run threads in backend
-2025-11-22 16:13:35,168 INFO    MainThread:1796 [wandb_run.py:_console_start():2504] atexit reg
-2025-11-22 16:13:35,168 INFO    MainThread:1796 [wandb_run.py:_redirect():2352] redirect: wrap_raw
-2025-11-22 16:13:35,168 INFO    MainThread:1796 [wandb_run.py:_redirect():2421] Wrapping output streams.
-2025-11-22 16:13:35,168 INFO    MainThread:1796 [wandb_run.py:_redirect():2444] Redirects installed.
-2025-11-22 16:13:35,176 INFO    MainThread:1796 [wandb_init.py:init():1080] run started, returning control to user process
-2025-11-22 16:14:07,413 INFO    MainThread:1796 [wandb_run.py:_config_callback():1385] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'float32', '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, 'architectures': ['BertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'O', 1: 'B-GUJ', 2: 'I-GUJ', 3: 'B-ENG', 4: 'I-ENG'}, 'label2id': {'O': 0, 'B-GUJ': 1, 'I-GUJ': 2, 'B-ENG': 3, 'I-ENG': 4}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, '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, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'bert-base-multilingual-cased', 'transformers_version': '4.57.1', 'directionality': 'bidi', 'model_type': 'bert', 'pooler_fc_size': 768, 'pooler_num_attention_heads': 12, 'pooler_num_fc_layers': 3, 'pooler_size_per_head': 128, 'pooler_type': 'first_token_transform', 'tf_legacy_loss': False, 'use_bfloat16': False, 'vocab_size': 119547, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_attentions': False, 'output_dir': './models/bert-multilingual-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/bert-multilingual-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': 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': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, '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, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', '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': 'h3110Fr13nd/guj-eng-code-switch-bert-multilingual-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-bert-multilingual-data2', '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, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
-2025-11-22 16:14:07,419 INFO    MainThread:1796 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 177266693 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x78d561625010>>
-2025-11-22 16:14:07,419 INFO    MainThread:1796 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 177266693 None
-2025-11-22 16:18:08,618 INFO    MainThread:1796 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/76f9jnsn
-2025-11-22 16:18:08,620 INFO    MainThread:1796 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
-2025-11-22 16:18:08,620 INFO    MainThread:1796 [wandb_run.py:_restore():2451] restore
-2025-11-22 16:18:08,620 INFO    MainThread:1796 [wandb_run.py:_restore():2457] restore done
-2025-11-22 16:18:09,283 INFO    MainThread:1796 [wandb_run.py:_footer_sync_info():3853] logging synced files
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:init():888] starting backend
+2025-11-22 17:36:30,292 INFO    MainThread:1459 [wandb_init.py:init():891] sending inform_init request
+2025-11-22 17:36:30,301 INFO    MainThread:1459 [wandb_init.py:init():899] backend started and connected
+2025-11-22 17:36:30,304 INFO    MainThread:1459 [wandb_init.py:init():969] updated telemetry
+2025-11-22 17:36:30,311 INFO    MainThread:1459 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
+2025-11-22 17:36:31,052 INFO    MainThread:1459 [wandb_init.py:init():1040] starting run threads in backend
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_console_start():2504] atexit reg
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_redirect():2352] redirect: wrap_raw
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_redirect():2421] Wrapping output streams.
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_redirect():2444] Redirects installed.
+2025-11-22 17:36:31,556 INFO    MainThread:1459 [wandb_init.py:init():1080] run started, returning control to user process
+2025-11-22 17:36:55,547 INFO    MainThread:1459 [wandb_run.py:_config_callback():1385] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'float32', '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, 'architectures': ['BertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'O', 1: 'B-GUJ', 2: 'I-GUJ', 3: 'B-ENG', 4: 'I-ENG'}, 'label2id': {'O': 0, 'B-GUJ': 1, 'I-GUJ': 2, 'B-ENG': 3, 'I-ENG': 4}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, '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, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'bert-base-multilingual-cased', 'transformers_version': '4.57.1', 'directionality': 'bidi', 'model_type': 'bert', 'pooler_fc_size': 768, 'pooler_num_attention_heads': 12, 'pooler_num_fc_layers': 3, 'pooler_size_per_head': 128, 'pooler_type': 'first_token_transform', 'tf_legacy_loss': False, 'use_bfloat16': False, 'vocab_size': 119547, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_attentions': False, 'output_dir': './models/bert-multilingual-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/bert-multilingual-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': 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': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, '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, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', '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': 'h3110Fr13nd/guj-eng-code-switch-bert-multilingual-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-bert-multilingual-data2', '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, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2025-11-22 17:36:55,553 INFO    MainThread:1459 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 177266693 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7aae6e5964e0>>
+2025-11-22 17:36:55,553 INFO    MainThread:1459 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 177266693 None
+2025-11-22 17:43:27,008 INFO    MainThread:1459 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/7f2wzkw5
+2025-11-22 17:43:27,010 INFO    MainThread:1459 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
+2025-11-22 17:43:27,010 INFO    MainThread:1459 [wandb_run.py:_restore():2451] restore
+2025-11-22 17:43:27,011 INFO    MainThread:1459 [wandb_run.py:_restore():2457] restore done
+2025-11-22 17:43:28,797 INFO    MainThread:1459 [wandb_run.py:_footer_sync_info():3853] logging synced files

wandb_logs/run-20251122_173629-7f2wzkw5/files/config.yaml

@@ -0,0 +1,543 @@
+_name_or_path:
+    value: bert-base-multilingual-cased
+_wandb:
+    value:
+        cli_version: 0.23.0
+        e:
+            zyfw9xtja269bha0ppac3mxoy5904j9p:
+                args:
+                    - configs/bert_data2.json
+                codePath: train.py
+                codePathLocal: train.py
+                cpu_count: 1
+                cpu_count_logical: 2
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "120942624768"
+                        used: "41433153536"
+                email: vijaysinghkushwaha3737@gmail.com
+                executable: /usr/bin/python3
+                git:
+                    commit: c280afc6ba26ad46a6cf9a434272dbf927fafc80
+                    remote: https://h3110Fr13nd:@github.com/h3110Fr13nd/code-switch-identification-model.git
+                gpu: Tesla T4
+                gpu_count: 1
+                gpu_nvidia:
+                    - architecture: Turing
+                      cudaCores: 2560
+                      memoryTotal: "16106127360"
+                      name: Tesla T4
+                      uuid: GPU-1b701237-0e57-cd79-3d08-bb01f3fff16f
+                host: 8b09dd3d6919
+                memory:
+                    total: "13605851136"
+                os: Linux-6.6.105+-x86_64-with-glibc2.35
+                program: /content/code-switch-identification-model/train.py
+                python: CPython 3.12.12
+                root: /content/code-switch-identification-model
+                startedAt: "2025-11-22T17:36:29.567968Z"
+                writerId: zyfw9xtja269bha0ppac3mxoy5904j9p
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.12.12
+        t:
+            "1":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 51
+                - 53
+                - 71
+                - 98
+                - 100
+                - 105
+            "2":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 51
+                - 53
+                - 71
+                - 98
+                - 100
+                - 105
+            "3":
+                - 2
+                - 7
+                - 13
+                - 15
+                - 16
+                - 19
+                - 62
+                - 66
+            "4": 3.12.12
+            "5": 0.23.0
+            "6": 4.57.1
+            "9":
+                "1": transformers_trainer
+            "12": 0.23.0
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+adafactor:
+    value: false
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+add_cross_attention:
+    value: false
+architectures:
+    value:
+        - BertForMaskedLM
+attention_probs_dropout_prob:
+    value: 0.1
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+bad_words_ids:
+    value: null
+batch_eval_metrics:
+    value: false
+batch_size:
+    value: 16
+begin_suppress_tokens:
+    value: null
+bf16:
+    value: false
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: null
+chunk_size_feed_forward:
+    value: 0
+classifier_dropout:
+    value: null
+cross_attention_hidden_size:
+    value: null
+data_seed:
+    value: null
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+decoder_start_token_id:
+    value: null
+deepspeed:
+    value: null
+directionality:
+    value: bidi
+disable_tqdm:
+    value: false
+diversity_penalty:
+    value: 0
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_sample:
+    value: false
+do_train:
+    value: false
+dtype:
+    value: float32
+early_stopping:
+    value: false
+encoder_no_repeat_ngram_size:
+    value: 0
+eos_token_id:
+    value: null
+epochs:
+    value: 3
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: null
+eval_strategy:
+    value: epoch
+eval_use_gather_object:
+    value: false
+exponential_decay_length_penalty:
+    value: null
+finetuning_task:
+    value: null
+forced_bos_token_id:
+    value: null
+forced_eos_token_id:
+    value: null
+fp16:
+    value: false
+fp16_backend:
+    value: auto
+fp16_full_eval:
+    value: false
+fp16_opt_level:
+    value: O1
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+fsdp_min_num_params:
+    value: 0
+fsdp_transformer_layer_cls_to_wrap:
+    value: null
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 1
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: true
+group_by_length:
+    value: false
+half_precision_backend:
+    value: auto
+hidden_act:
+    value: gelu
+hidden_dropout_prob:
+    value: 0.1
+hidden_size:
+    value: 768
+hub_always_push:
+    value: false
+hub_model_id:
+    value: h3110Fr13nd/guj-eng-code-switch-bert-multilingual-data2
+hub_private_repo:
+    value: false
+hub_revision:
+    value: null
+hub_strategy:
+    value: end
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": O
+        "1": B-GUJ
+        "2": I-GUJ
+        "3": B-ENG
+        "4": I-ENG
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_inputs_for_metrics:
+    value: false
+include_num_input_tokens_seen:
+    value: "no"
+include_tokens_per_second:
+    value: false
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 3072
+is_decoder:
+    value: false
+is_encoder_decoder:
+    value: false
+jit_mode_eval:
+    value: false
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        B-ENG: 3
+        B-GUJ: 1
+        I-ENG: 4
+        I-GUJ: 2
+        O: 0
+layer_norm_eps:
+    value: 1e-12
+learning_rate:
+    value: 2e-05
+length_column_name:
+    value: length
+length_penalty:
+    value: 1
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: true
+local_rank:
+    value: 0
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_dir:
+    value: ./models/bert-multilingual-data2/logs
+logging_first_step:
+    value: true
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 50
+logging_strategy:
+    value: steps
+lr_scheduler_type:
+    value: linear
+max_grad_norm:
+    value: 1
+max_length:
+    value: 20
+max_position_embeddings:
+    value: 512
+max_steps:
+    value: -1
+metric_for_best_model:
+    value: f1
+min_length:
+    value: 0
+model:
+    value: bert-base-multilingual-cased
+model/num_parameters:
+    value: 177266693
+model_type:
+    value: bert
+mp_parameters:
+    value: ""
+neftune_noise_alpha:
+    value: null
+no_cuda:
+    value: false
+no_repeat_ngram_size:
+    value: 0
+num_attention_heads:
+    value: 12
+num_beam_groups:
+    value: 1
+num_beams:
+    value: 1
+num_hidden_layers:
+    value: 12
+num_return_sequences:
+    value: 1
+num_train_epochs:
+    value: 3
+optim:
+    value: adamw_torch_fused
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: ./models/bert-multilingual-data2
+output_hidden_states:
+    value: false
+output_scores:
+    value: false
+overwrite_output_dir:
+    value: true
+pad_token_id:
+    value: 0
+parallelism_config:
+    value: null
+past_index:
+    value: -1
+per_device_eval_batch_size:
+    value: 32
+per_device_train_batch_size:
+    value: 16
+per_gpu_eval_batch_size:
+    value: null
+per_gpu_train_batch_size:
+    value: null
+pooler_fc_size:
+    value: 768
+pooler_num_attention_heads:
+    value: 12
+pooler_num_fc_layers:
+    value: 3
+pooler_size_per_head:
+    value: 128
+pooler_type:
+    value: first_token_transform
+position_embedding_type:
+    value: absolute
+prediction_loss_only:
+    value: false
+prefix:
+    value: null
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: true
+push_to_hub_model_id:
+    value: guj-eng-code-switch-bert-multilingual-data2
+push_to_hub_organization:
+    value: null
+push_to_hub_token:
+    value: <PUSH_TO_HUB_TOKEN>
+ray_scope:
+    value: last
+remove_invalid_values:
+    value: false
+remove_unused_columns:
+    value: true
+repetition_penalty:
+    value: 1
+report_to:
+    value:
+        - tensorboard
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+return_dict_in_generate:
+    value: false
+run_name:
+    value: null
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_safetensors:
+    value: true
+save_steps:
+    value: null
+save_strategy:
+    value: epoch
+save_total_limit:
+    value: 3
+seed:
+    value: 42
+sep_token_id:
+    value: null
+skip_memory_metrics:
+    value: true
+suppress_tokens:
+    value: null
+task_specific_params:
+    value: null
+temperature:
+    value: 1
+tf_legacy_loss:
+    value: false
+tf32:
+    value: null
+tie_encoder_decoder:
+    value: false
+tie_word_embeddings:
+    value: true
+tokenizer_class:
+    value: null
+top_k:
+    value: 50
+top_p:
+    value: 1
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+torchdynamo:
+    value: null
+torchscript:
+    value: false
+tpu_metrics_debug:
+    value: false
+tpu_num_cores:
+    value: null
+trackio_space_id:
+    value: trackio
+train_file:
+    value: synthetic_data_gen/data2/train.txt
+transformers_version:
+    value: 4.57.1
+type_vocab_size:
+    value: 2
+typical_p:
+    value: 1
+use_bfloat16:
+    value: false
+use_cache:
+    value: true
+use_cpu:
+    value: false
+use_legacy_prediction_loop:
+    value: false
+use_liger_kernel:
+    value: false
+use_mps_device:
+    value: false
+vocab_size:
+    value: 119547
+warmup_ratio:
+    value: 0.1
+warmup_steps:
+    value: 0
+weight_decay:
+    value: 0.01

wandb_logs/run-20251122_173629-7f2wzkw5/files/output.log

@@ -0,0 +1,88 @@
+
+    _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|
+    _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|
+    _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|
+    _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|
+    _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|
+Enter your token (input will not be visible):
+
+Cannot authenticate through git-credential as no helper is defined on your machine.
+You might have to re-authenticate when pushing to the Hugging Face Hub.
+Run the following command in your terminal in case you want to set the 'store' credential helper as default.
+
+git config --global credential.helper store
+
+Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.
+Token has not been saved to git credential helper.
+WARNING:huggingface_hub._login:Token has not been saved to git credential helper.
+tokenizer_config.json: 100% 49.0/49.0 [00:00<00:00, 214kB/s]
+config.json: 100% 625/625 [00:00<00:00, 2.74MB/s]
+vocab.txt: 100% 996k/996k [00:00<00:00, 1.59MB/s]
+tokenizer.json: 100% 1.96M/1.96M [00:00<00:00, 4.44MB/s]
+model.safetensors: 100% 714M/714M [00:06<00:00, 113MB/s]  
+Some weights of BertForTokenClassification were not initialized from the model checkpoint at bert-base-multilingual-cased and are newly initialized: ['classifier.bias', 'classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+Downloading builder script: 6.34kB [00:00, 8.22MB/s]
+{'loss': 1.6736, 'grad_norm': 9.364067077636719, 'learning_rate': 0.0, 'epoch': 0.0}
+{'loss': 1.1254, 'grad_norm': 10.865610122680664, 'learning_rate': 1.3066666666666668e-05, 'epoch': 0.2}
+{'loss': 0.3817, 'grad_norm': 3.5892016887664795, 'learning_rate': 1.928888888888889e-05, 'epoch': 0.4}
+{'loss': 0.1743, 'grad_norm': 5.089068412780762, 'learning_rate': 1.780740740740741e-05, 'epoch': 0.6}
+{'loss': 0.1315, 'grad_norm': 2.536372423171997, 'learning_rate': 1.632592592592593e-05, 'epoch': 0.8}
+{'loss': 0.0932, 'grad_norm': 2.548548698425293, 'learning_rate': 1.4844444444444445e-05, 'epoch': 1.0}
+100% 750/750 [04:59<00:00,  2.50it/s]
+Processing Files (3 / 3)      : 100% 709M/709M [00:29<00:00, 24.4MB/s, 5.22MB/s  ]    
+{'eval_loss': 0.10810670256614685, 'eval_precision': 0.9037234042553192, 'eval_recall': 0.9208672086720867, 'eval_f1': 0.9122147651006711, 'eval_accuracy': 0.970992733169179, 'eval_runtime': 5.4132, 'eval_samples_per_second': 92.367, 'eval_steps_per_second': 2.956, 'epoch': 1.0}
+{'loss': 0.0745, 'grad_norm': 1.2293448448181152, 'learning_rate': 1.3362962962962964e-05, 'epoch': 1.2}
+{'loss': 0.0569, 'grad_norm': 2.833926200866699, 'learning_rate': 1.1881481481481482e-05, 'epoch': 1.4}
+{'loss': 0.0776, 'grad_norm': 2.0456528663635254, 'learning_rate': 1.04e-05, 'epoch': 1.6}
+{'loss': 0.0641, 'grad_norm': 2.135941743850708, 'learning_rate': 8.91851851851852e-06, 'epoch': 1.8}
+{'loss': 0.0758, 'grad_norm': 2.974154233932495, 'learning_rate': 7.437037037037038e-06, 'epoch': 2.0}
+{'eval_loss': 0.09071356058120728, 'eval_precision': 0.9241047568145376, 'eval_recall': 0.9371273712737127, 'eval_f1': 0.9305705059203444, 'eval_accuracy': 0.977658999459492, 'eval_runtime': 4.4008, 'eval_samples_per_second': 113.615, 'eval_steps_per_second': 3.636, 'epoch': 2.0}
+{'loss': 0.0509, 'grad_norm': 0.6356647610664368, 'learning_rate': 5.955555555555555e-06, 'epoch': 2.2}
+{'loss': 0.0473, 'grad_norm': 2.004117727279663, 'learning_rate': 4.4740740740740746e-06, 'epoch': 2.4}
+{'loss': 0.0354, 'grad_norm': 0.2392495572566986, 'learning_rate': 2.992592592592593e-06, 'epoch': 2.6}
+{'loss': 0.0317, 'grad_norm': 1.2536988258361816, 'learning_rate': 1.5111111111111112e-06, 'epoch': 2.8}
+{'loss': 0.0348, 'grad_norm': 1.0227235555648804, 'learning_rate': 2.9629629629629632e-08, 'epoch': 3.0}
+{'eval_loss': 0.09460805356502533, 'eval_precision': 0.927038626609442, 'eval_recall': 0.9365853658536586, 'eval_f1': 0.9317875438123484, 'eval_accuracy': 0.9788000720677437, 'eval_runtime': 4.3756, 'eval_samples_per_second': 114.271, 'eval_steps_per_second': 3.657, 'epoch': 3.0}
+{'train_runtime': 299.4505, 'train_samples_per_second': 40.073, 'train_steps_per_second': 2.505, 'train_loss': 0.16440406481424968, 'epoch': 3.0}
+New Data Upload               : 100% 644M/644M [00:29<00:00, 22.2MB/s, 5.22MB/s  ] 
+  ...l-data2/training_args.bin: 100% 5.97k/5.97k [00:28<?, ?B/s]
+  ...l-data2/model.safetensors: 100% 709M/709M [00:26<00:00, 26.7MB/s] 
+  ...33015.8b09dd3d6919.1459.0: 100% 10.6k/10.6k [00:18<00:00, 527B/s]  
+Processing Files (3 / 3)      : 100% 709M/709M [00:06<00:00, 111MB/s,  109MB/s  ] 
+New Data Upload               : 100% 1.28M/1.28M [00:06<00:00, 200kB/s,  207kB/s  ]
+  ...l-data2/training_args.bin: 100% 5.97k/5.97k [00:06<?, ?B/s]
+  ...33015.8b09dd3d6919.1459.0: 100% 10.6k/10.6k [00:06<?, ?B/s]
+  ...l-data2/model.safetensors: 100% 709M/709M [00:06<00:00, 109MB/s] 
+No files have been modified since last commit. Skipping to prevent empty commit.
+WARNING:huggingface_hub.hf_api:No files have been modified since last commit. Skipping to prevent empty commit.
+***** train metrics *****
+  epoch                    =        3.0
+  total_flos               =   489613GF
+  train_loss               =     0.1644
+  train_runtime            = 0:04:59.45
+  train_samples_per_second =     40.073
+  train_steps_per_second   =      2.505
+100% 16/16 [00:04<00:00,  3.75it/s]
+***** eval metrics *****
+  epoch                   =        3.0
+  eval_accuracy           =     0.9788
+  eval_f1                 =     0.9318
+  eval_loss               =     0.0946
+  eval_precision          =      0.927
+  eval_recall             =     0.9366
+  eval_runtime            = 0:00:04.44
+  eval_samples_per_second =    112.366
+  eval_steps_per_second   =      3.596
+100% 16/16 [00:02<00:00,  5.79it/s]early stopping required metric_for_best_model, but did not find eval_f1 so early stopping is disabled
+100% 16/16 [00:04<00:00,  3.75it/s]
+***** test metrics *****
+  epoch                   =        3.0
+  test_accuracy           =     0.9884
+  test_f1                 =      0.946
+  test_loss               =     0.0453
+  test_precision          =     0.9455
+  test_recall             =     0.9465
+  test_runtime            = 0:00:04.48
+  test_samples_per_second =    111.603
+  test_steps_per_second   =      3.571

wandb_logs/run-20251122_173629-7f2wzkw5/files/requirements.txt

@@ -0,0 +1,698 @@
+setuptools==75.2.0
+pip==24.1.2
+requirements-parser==0.9.0
+types-setuptools==80.9.0.20250822
+ipykernel==7.1.0
+tensorboard==2.20.0
+numpy==2.3.5
+pyarrow==22.0.0
+matplotlib==3.10.7
+widgetsnbextension==4.0.15
+seqeval==1.2.2
+ipywidgets==8.1.8
+datasets==4.4.1
+pandas==2.3.3
+comm==0.2.3
+google-genai==1.50.1
+scikit-learn==1.7.2
+evaluate==0.4.6
+jedi==0.19.2
+jupyter_client==8.6.3
+google-colab==1.0.0
+httpcore==1.0.9
+colorlover==0.3.0
+pyOpenSSL==24.2.1
+PySocks==1.7.1
+fsspec==2025.3.0
+google-ai-generativelanguage==0.6.15
+dlib==19.24.6
+fastdownload==0.0.7
+jaxlib==0.7.2
+python-multipart==0.0.20
+nltk==3.9.1
+chardet==5.2.0
+pyparsing==3.2.5
+sentry-sdk==2.45.0
+audioread==3.1.0
+langchain-core==0.3.80
+jaraco.classes==3.4.0
+cymem==2.0.13
+vega-datasets==0.9.0
+docstring_parser==0.17.0
+nest-asyncio==1.6.0
+mlxtend==0.23.4
+xyzservices==2025.10.0
+more-itertools==10.8.0
+torchao==0.10.0
+numba==0.60.0
+panel==1.8.3
+docutils==0.21.2
+holoviews==1.22.0
+attrs==25.4.0
+db-dtypes==1.4.4
+tabulate==0.9.0
+pydotplus==2.0.2
+soundfile==0.13.1
+sklearn-pandas==2.2.0
+multitasking==0.0.12
+glob2==0.7
+nvidia-cusolver-cu12==11.7.1.2
+google-adk==1.17.0
+alabaster==1.0.0
+mdit-py-plugins==0.5.0
+intel-cmplr-lib-ur==2025.3.1
+nvidia-cufft-cu12==11.3.0.4
+google-cloud-bigquery-connection==1.19.0
+polars==1.31.0
+openai==1.109.1
+google-cloud-spanner==3.59.0
+patsy==1.0.2
+pytest==8.4.2
+pycparser==2.23
+curl_cffi==0.13.0
+linkify-it-py==2.0.3
+imutils==0.5.4
+Markdown==3.10
+pandas-stubs==2.2.2.240909
+pooch==1.8.2
+pandas-gbq==0.30.0
+google-cloud-dataproc==5.23.0
+google-cloud-language==2.18.0
+jupyter_kernel_gateway==2.5.2
+google-resumable-media==2.8.0
+nvidia-cuda-runtime-cu12==12.6.77
+dask-cudf-cu12==25.10.0
+websocket-client==1.9.0
+distributed-ucxx-cu12==0.46.0
+altair==5.5.0
+idna==3.11
+wandb==0.23.0
+moviepy==1.0.3
+click==8.3.1
+oauth2client==4.1.3
+GDAL==3.8.4
+mcp==1.21.2
+pyzmq==26.2.1
+langsmith==0.4.43
+sqlparse==0.5.3
+betterproto==2.0.0b6
+parso==0.8.5
+imbalanced-learn==0.14.0
+tbb==2022.3.0
+dm-tree==0.1.9
+cuda-python==12.9.4
+pygit2==1.19.0
+proglog==0.1.12
+fastjsonschema==2.21.2
+tornado==6.5.1
+matplotlib-venn==1.1.2
+Authlib==1.6.5
+cryptography==43.0.3
+snowballstemmer==3.0.1
+networkx==3.5
+nvidia-cublas-cu12==12.6.4.1
+wcwidth==0.2.14
+dopamine_rl==4.1.2
+blobfile==3.1.0
+simple-parsing==0.1.7
+pylibcugraph-cu12==25.10.1
+sentence-transformers==5.1.2
+jsonpatch==1.33
+webencodings==0.5.1
+zict==3.0.0
+google-cloud-bigquery-storage==2.34.0
+sphinxcontrib-serializinghtml==2.0.0
+uc-micro-py==1.0.3
+rfc3987-syntax==1.1.0
+itsdangerous==2.2.0
+peft==0.18.0
+gspread-dataframe==4.0.0
+pydot==3.0.4
+pydantic_core==2.33.2
+oauthlib==3.3.1
+google-cloud-bigquery==3.38.0
+geopy==2.4.1
+rmm-cu12==25.10.0
+distributed==2025.9.1
+pandocfilters==1.5.1
+llvmlite==0.43.0
+torchaudio==2.9.0+cu126
+hdbscan==0.8.40
+safetensors==0.7.0
+et_xmlfile==2.0.0
+numexpr==2.14.1
+scs==3.2.9
+importlib_resources==6.5.2
+pyogrio==0.11.1
+rapids-logger==0.1.19
+google==2.0.3
+blinker==1.9.0
+colour==0.1.5
+lightgbm==4.6.0
+pylibraft-cu12==25.10.0
+autograd==1.8.0
+duckdb==1.3.2
+typing_extensions==4.15.0
+protobuf==5.29.5
+argon2-cffi==25.1.0
+Bottleneck==1.4.2
+libucxx-cu12==0.46.0
+libcugraph-cu12==25.10.1
+huggingface-hub==0.36.0
+fastapi==0.121.3
+mistune==3.1.4
+pyspark==3.5.1
+ibis-framework==9.5.0
+tqdm==4.67.1
+seaborn==0.13.2
+mdurl==0.1.2
+stumpy==1.13.0
+python-dotenv==1.2.1
+psygnal==0.15.0
+music21==9.3.0
+Farama-Notifications==0.0.4
+jsonschema-specifications==2025.9.1
+xxhash==3.6.0
+confection==0.1.5
+treelite==4.4.1
+httpimport==1.4.1
+libpysal==4.13.0
+cramjam==2.11.0
+google-cloud-functions==1.21.0
+grpcio-status==1.71.2
+torchsummary==1.5.1
+nvidia-nvshmem-cu12==3.3.20
+libucx-cu12==1.19.0
+geopandas==1.1.1
+toml==0.10.2
+shapely==2.1.2
+html5lib==1.1
+antlr4-python3-runtime==4.9.3
+clarabel==0.11.1
+uvicorn==0.38.0
+toolz==0.12.1
+cloudpathlib==0.23.0
+cupy-cuda12x==13.6.0
+fastai==2.8.5
+peewee==3.18.3
+GitPython==3.1.45
+aiohappyeyeballs==2.6.1
+murmurhash==1.0.15
+jax-cuda12-plugin==0.7.2
+pyperclip==1.11.0
+promise==2.3
+jupyter_server==2.14.0
+webcolors==25.10.0
+imagesize==1.4.1
+prettytable==3.17.0
+alembic==1.17.2
+progressbar2==4.5.0
+requests==2.32.4
+nvidia-ml-py==13.580.82
+humanize==4.14.0
+umap-learn==0.5.9.post2
+h5netcdf==1.7.3
+PyGObject==3.42.0
+google-cloud-aiplatform==1.128.0
+flatbuffers==25.9.23
+optax==0.2.6
+nvidia-cuda-cupti-cu12==12.6.80
+nx-cugraph-cu12==25.10.0
+lark==1.3.1
+tenacity==8.5.0
+entrypoints==0.4
+prompt_toolkit==3.0.52
+fonttools==4.60.1
+ffmpy==1.0.0
+google-cloud-core==2.5.0
+matplotlib-inline==0.2.1
+sphinxcontrib-jsmath==1.0.1
+ply==3.11
+tweepy==4.16.0
+en_core_web_sm==3.8.0
+google-crc32c==1.7.1
+libcudf-cu12==25.10.0
+ipytree==0.2.2
+ImageIO==2.37.2
+rfc3339-validator==0.1.4
+keras==3.10.0
+opt_einsum==3.4.0
+jupyter_server_terminals==0.5.3
+rpds-py==0.29.0
+threadpoolctl==3.6.0
+urllib3==2.5.0
+kagglehub==0.3.13
+Flask==3.1.2
+easydict==1.13
+grpcio==1.76.0
+ratelim==0.1.6
+logical-unification==0.4.7
+omegaconf==2.3.0
+roman-numerals-py==3.1.0
+dataproc-spark-connect==0.8.3
+langchain-text-splitters==0.3.11
+tinycss2==1.4.0
+python-json-logger==4.0.0
+scikit-image==0.25.2
+highspy==1.12.0
+tf-slim==1.1.0
+torchtune==0.6.1
+jupyter-console==6.6.3
+spanner-graph-notebook==1.1.8
+dill==0.3.8
+tensorboard-data-server==0.7.2
+slicer==0.0.8
+keyring==25.7.0
+arviz==0.22.0
+sympy==1.13.3
+google-cloud-resource-manager==1.15.0
+traittypes==0.2.3
+typer-slim==0.20.0
+annotated-doc==0.0.4
+hf-xet==1.2.0
+dask-cuda==25.10.0
+pymc==5.26.1
+pynndescent==0.5.13
+stanio==0.5.1
+treescope==0.1.10
+optree==0.18.0
+propcache==0.4.1
+rich==13.9.4
+gcsfs==2025.3.0
+torch==2.9.0+cu126
+MarkupSafe==3.0.3
+tzlocal==5.3.1
+google-cloud-secret-manager==2.25.0
+atpublic==5.1
+gitdb==4.0.12
+ruff==0.14.5
+opentelemetry-exporter-gcp-monitoring==1.11.0a0
+grpc-interceptor==0.15.4
+opentelemetry-exporter-gcp-logging==1.11.0a0
+fqdn==1.5.1
+soxr==1.0.0
+hf_transfer==0.1.9
+pyasn1==0.6.1
+geemap==0.35.3
+regex==2024.11.6
+ipython-sql==0.5.0
+pyviz_comms==3.0.6
+pydub==0.25.1
+geographiclib==2.1
+Jinja2==3.1.6
+ipython-genutils==0.2.0
+multiprocess==0.70.16
+h11==0.16.0
+tables==3.10.2
+tensorflow-text==2.19.0
+bokeh==3.7.3
+opentelemetry-resourcedetector-gcp==1.11.0a0
+beautifulsoup4==4.13.5
+filelock==3.20.0
+catalogue==2.0.10
+fasttransform==0.0.2
+typeguard==4.4.4
+openpyxl==3.1.5
+tokenizers==0.22.1
+plotly==5.24.1
+ucxx-cu12==0.46.0
+branca==0.8.2
+overrides==7.7.0
+cuda-core==0.3.2
+tensorflow-probability==0.25.0
+xarray-einstats==0.9.1
+tf_keras==2.19.0
+referencing==0.37.0
+argon2-cffi-bindings==25.1.0
+librmm-cu12==25.10.0
+nvidia-cusparse-cu12==12.5.4.2
+google-cloud-discoveryengine==0.13.12
+xgboost==3.1.1
+diffusers==0.35.2
+timm==1.0.22
+PyDrive2==1.21.3
+tblib==3.2.2
+scooby==0.11.0
+opencv-python-headless==4.12.0.88
+wheel==0.45.1
+firebase-admin==6.9.0
+shap==0.50.0
+jsonpointer==3.0.0
+python-louvain==0.16
+charset-normalizer==3.4.4
+sqlglot==25.20.2
+jsonschema==4.25.1
+jieba==0.42.1
+importlib_metadata==8.7.0
+nvidia-cuda-nvrtc-cu12==12.6.77
+editdistance==0.8.1
+jax==0.7.2
+google-api-core==2.28.1
+shellingham==1.5.4
+portpicker==1.5.2
+cudf-cu12==25.10.0
+gspread==6.2.1
+pylibcudf-cu12==25.10.0
+python-slugify==8.0.4
+anywidget==0.9.21
+distro==1.9.0
+stringzilla==4.2.3
+libcuml-cu12==25.10.0
+graphviz==0.21
+ipython==7.34.0
+hyperopt==0.2.7
+sniffio==1.3.1
+python-utils==3.9.1
+bigframes==2.29.1
+folium==0.20.0
+google-cloud-bigtable==2.34.0
+text-unidecode==1.3
+pydantic-settings==2.12.0
+annotated-types==0.7.0
+locket==1.0.0
+pyproj==3.7.2
+orbax-checkpoint==0.11.28
+PyJWT==2.10.1
+natsort==8.4.0
+astropy-iers-data==0.2025.11.10.0.38.31
+gym-notices==0.1.0
+debugpy==1.8.15
+weasel==0.4.3
+PyOpenGL==3.1.10
+pydata-google-auth==1.9.1
+semantic-version==2.10.0
+google-cloud-firestore==2.21.0
+statsmodels==0.14.5
+pycocotools==2.0.10
+greenlet==3.2.4
+Werkzeug==3.1.3
+preshed==3.0.12
+gymnasium==1.2.2
+prometheus_client==0.23.1
+triton==3.5.0
+frozendict==2.4.7
+multipledispatch==1.0.0
+srsly==2.5.2
+google-auth-httplib2==0.2.1
+zstandard==0.25.0
+uri-template==1.3.0
+gradio==5.49.1
+websockets==15.0.1
+bigquery-magics==0.10.3
+nvidia-cuda-nvcc-cu12==12.5.82
+etils==1.13.0
+cufflinks==0.17.3
+simsimd==6.5.3
+frozenlist==1.8.0
+transformers==4.57.1
+ale-py==0.11.2
+orjson==3.11.4
+jiter==0.12.0
+safehttpx==0.1.7
+google-auth==2.38.0
+inflect==7.5.0
+decorator==4.4.2
+types-pytz==2025.2.0.20251108
+cyipopt==1.5.0
+imageio-ffmpeg==0.6.0
+pyshp==3.0.2.post1
+grpc-google-iam-v1==0.14.3
+immutabledict==4.2.2
+ipyparallel==8.8.0
+beartype==0.22.5
+keras-nlp==0.21.1
+tensorflow-hub==0.16.1
+yfinance==0.2.66
+cuda-toolkit==12.9.1
+googleapis-common-protos==1.72.0
+google-generativeai==0.8.5
+aiofiles==24.1.0
+joblib==1.5.2
+ndindex==1.10.1
+nbformat==5.10.4
+pygame==2.6.1
+opentelemetry-proto==1.37.0
+cachetools==5.5.2
+sphinxcontrib-qthelp==2.0.0
+albumentations==2.0.8
+libraft-cu12==25.10.0
+absl-py==1.4.0
+simplejson==3.20.2
+jupytext==1.17.3
+raft-dask-cu12==25.10.0
+pyomo==6.9.5
+msgpack==1.1.2
+tensorflow==2.19.0
+dask==2025.9.1
+aiohttp==3.13.2
+future==1.0.0
+bleach==6.3.0
+cmdstanpy==1.3.0
+wurlitzer==3.1.1
+libkvikio-cu12==25.10.0
+google-cloud-audit-log==0.4.0
+packaging==25.0
+defusedxml==0.7.1
+google-auth-oauthlib==1.2.3
+textblob==0.19.0
+pexpect==4.9.0
+Mako==1.3.10
+cmake==3.31.6
+eerepr==0.1.2
+namex==0.1.0
+sse-starlette==3.0.3
+grpclib==0.4.8
+jaraco.context==6.0.1
+nbclient==0.10.2
+scipy==1.16.3
+miniKanren==1.0.5
+nvidia-curand-cu12==10.3.7.77
+sphinxcontrib-applehelp==2.0.0
+python-dateutil==2.9.0.post0
+librosa==0.11.0
+ptyprocess==0.7.0
+opentelemetry-api==1.37.0
+nvtx==0.2.13
+nvidia-cufile-cu12==1.11.1.6
+plum-dispatch==2.6.0
+kiwisolver==1.4.9
+ipyleaflet==0.20.0
+jaraco.functools==4.3.0
+terminado==0.18.1
+tensorflow_decision_forests==1.12.0
+Send2Trash==1.8.3
+flax==0.10.7
+PyWavelets==1.9.0
+brotli==1.2.0
+mpmath==1.3.0
+earthengine-api==1.5.24
+isoduration==20.11.0
+pytz==2025.2
+tiktoken==0.12.0
+traitlets==5.7.1
+typer==0.20.0
+plotnine==0.14.5
+sphinxcontrib-devhelp==2.0.0
+spacy==3.8.11
+gym==0.25.2
+google-cloud-datastore==2.21.0
+torchdata==0.11.0
+bqplot==0.12.45
+missingno==0.5.2
+nvidia-cudnn-cu12==9.10.2.21
+param==2.3.0
+tensorstore==0.1.79
+ipyfilechooser==0.6.0
+rfc3986-validator==0.1.1
+nibabel==5.3.2
+starlette==0.50.0
+psutil==5.9.5
+lazy_loader==0.4
+smart_open==7.5.0
+jupyter_core==5.9.1
+pycairo==1.29.0
+pytensor==2.35.1
+hpack==4.1.0
+smmap==5.0.2
+httplib2==0.31.0
+h2==4.3.0
+nvidia-nccl-cu12==2.27.5
+googledrivedownloader==1.1.0
+SQLAlchemy==2.0.44
+yellowbrick==1.5
+cloudpickle==3.1.2
+typing-inspection==0.4.2
+cuml-cu12==25.10.0
+tensorflow-metadata==1.17.2
+hyperframe==6.1.0
+numba-cuda==0.19.1
+rpy2==3.5.17
+cuda-bindings==12.9.4
+langchain==0.3.27
+array_record==0.8.3
+google-cloud-appengine-logging==1.7.0
+requests-oauthlib==2.0.0
+lxml==5.4.0
+rsa==4.9.1
+thinc==8.3.10
+tomlkit==0.13.3
+blis==1.3.3
+opentelemetry-sdk==1.37.0
+kaggle==1.7.4.5
+tcmlib==1.4.1
+holidays==0.85
+multidict==6.7.0
+accelerate==1.11.0
+pyerfa==2.0.1.5
+babel==2.17.0
+google-api-python-client==2.187.0
+cffi==2.0.0
+soupsieve==2.8
+opencv-python==4.12.0.88
+rapids-dask-dependency==25.10.0
+chex==0.1.90
+google-cloud-translate==3.23.0
+python-snappy==0.7.3
+xarray==2025.11.0
+pillow==11.3.0
+uritemplate==4.2.0
+Cython==3.0.12
+tensorflow-datasets==4.9.9
+mkl==2025.2.0
+cvxpy==1.6.7
+spacy-loggers==1.0.5
+keyrings.google-artifactregistry-auth==1.1.2
+spacy-legacy==3.0.12
+fastrlock==0.8.3
+aiosignal==1.4.0
+osqp==1.0.5
+astunparse==1.6.3
+py-cpuinfo==9.0.0
+nbclassic==1.3.3
+pycryptodomex==3.23.0
+anyio==4.11.0
+ydf==0.13.0
+parsy==2.2
+einops==0.8.1
+iniconfig==2.3.0
+cycler==0.12.1
+h5py==3.15.1
+libclang==18.1.1
+gdown==5.2.0
+wasabi==1.1.3
+httpx==0.28.1
+termcolor==3.2.0
+umf==1.0.2
+mizani==0.13.5
+astropy==7.1.1
+opentelemetry-exporter-gcp-trace==1.11.0
+pandas-datareader==0.10.0
+nvidia-nvjitlink-cu12==12.6.85
+pickleshare==0.7.5
+community==1.0.0b1
+prophet==1.1.7
+jupyterlab_pygments==0.3.0
+requests-toolbelt==1.0.0
+gradio_client==1.13.3
+pydantic==2.11.10
+google-cloud-logging==3.12.1
+google-cloud-storage==2.19.0
+intel-openmp==2025.3.1
+tifffile==2025.10.16
+colorcet==3.1.0
+google-cloud-speech==2.34.0
+notebook_shim==0.2.4
+xlrd==2.0.2
+httpx-sse==0.4.3
+backcall==0.2.0
+blosc2==3.11.1
+sortedcontainers==2.4.0
+opentelemetry-exporter-otlp-proto-common==1.37.0
+sentencepiece==0.2.1
+six==1.17.0
+google-pasta==0.2.0
+sphinxcontrib-htmlhelp==2.1.0
+zipp==3.23.0
+jupyter-leaflet==0.20.0
+jeepney==0.9.0
+cons==0.4.7
+markdown-it-py==4.0.0
+wordcloud==1.9.4
+opencv-contrib-python==4.12.0.88
+opentelemetry-exporter-otlp-proto-http==1.37.0
+absolufy-imports==0.3.1
+psycopg2==2.9.11
+groovy==0.1.2
+CacheControl==0.14.4
+arrow==1.4.0
+ipyevents==2.0.4
+tzdata==2025.2
+nvidia-nvtx-cu12==12.6.77
+Sphinx==8.2.3
+tsfresh==0.21.1
+jupyter-events==0.12.0
+partd==1.4.2
+platformdirs==4.5.0
+SecretStorage==3.4.1
+narwhals==2.12.0
+sqlalchemy-spanner==1.17.1
+watchdog==6.0.0
+nbconvert==7.16.6
+google-cloud-trace==1.17.0
+cuda-pathfinder==1.3.2
+proto-plus==1.26.1
+notebook==6.5.7
+fastcore==1.8.16
+pluggy==1.6.0
+etuples==0.3.10
+gast==0.6.0
+PyYAML==6.0.3
+opentelemetry-semantic-conventions==0.58b0
+ml_dtypes==0.5.4
+google-cloud-monitoring==2.28.0
+pyasn1_modules==0.4.2
+cvxopt==1.3.2
+contourpy==1.3.3
+gin-config==0.5.0
+certifi==2025.11.12
+jsonpickle==4.1.1
+wrapt==2.0.1
+keras-hub==0.21.1
+torchvision==0.24.0+cu126
+yarl==1.22.0
+jupyterlab_widgets==3.0.16
+py4j==0.10.9.7
+Pygments==2.19.2
+python-box==7.3.2
+albucore==0.0.24
+nvidia-cuda-cccl-cu12==12.9.27
+jax-cuda12-pjrt==0.7.2
+fastprogress==1.0.3
+nvidia-cusparselt-cu12==0.7.1
+geocoder==1.38.1
+cudf-polars-cu12==25.10.0
+python-apt==0.0.0
+httplib2==0.20.2
+more-itertools==8.10.0
+oauthlib==3.2.0
+pyparsing==2.4.7
+PyGObject==3.42.1
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+PyJWT==2.3.0
+blinker==1.4
+python-apt==2.4.0+ubuntu4
+launchpadlib==1.10.16
+six==1.16.0
+zipp==1.0.0
+importlib-metadata==4.6.4
+dbus-python==1.2.18
+wadllib==1.3.6
+cryptography==3.4.8
+distro==1.7.0
+keyring==23.5.0
+SecretStorage==3.3.1
+jeepney==0.7.1
+Markdown==3.3.6
+Mako==1.1.3
+MarkupSafe==2.0.1

wandb_logs/run-20251122_173629-7f2wzkw5/files/wandb-metadata.json

@@ -0,0 +1,43 @@
+{
+  "os": "Linux-6.6.105+-x86_64-with-glibc2.35",
+  "python": "CPython 3.12.12",
+  "startedAt": "2025-11-22T17:36:29.567968Z",
+  "args": [
+    "configs/bert_data2.json"
+  ],
+  "program": "/content/code-switch-identification-model/train.py",
+  "codePath": "train.py",
+  "codePathLocal": "train.py",
+  "git": {
+    "remote": "https://h3110Fr13nd:@github.com/h3110Fr13nd/code-switch-identification-model.git",
+    "commit": "c280afc6ba26ad46a6cf9a434272dbf927fafc80"
+  },
+  "email": "vijaysinghkushwaha3737@gmail.com",
+  "root": "/content/code-switch-identification-model",
+  "host": "8b09dd3d6919",
+  "executable": "/usr/bin/python3",
+  "cpu_count": 1,
+  "cpu_count_logical": 2,
+  "gpu": "Tesla T4",
+  "gpu_count": 1,
+  "disk": {
+    "/": {
+      "total": "120942624768",
+      "used": "41433153536"
+    }
+  },
+  "memory": {
+    "total": "13605851136"
+  },
+  "gpu_nvidia": [
+    {
+      "name": "Tesla T4",
+      "memoryTotal": "16106127360",
+      "cudaCores": 2560,
+      "architecture": "Turing",
+      "uuid": "GPU-1b701237-0e57-cd79-3d08-bb01f3fff16f"
+    }
+  ],
+  "cudaVersion": "12.4",
+  "writerId": "zyfw9xtja269bha0ppac3mxoy5904j9p"
+}

wandb_logs/run-20251122_173629-7f2wzkw5/files/wandb-summary.json

@@ -0,0 +1 @@
+{"test/accuracy":0.9884382566585956,"test/steps_per_second":3.571,"train/learning_rate":2.9629629629629632e-08,"train_steps_per_second":2.505,"train/loss":0.0348,"train_samples_per_second":40.073,"eval/steps_per_second":3.596,"test/precision":0.9454937938478144,"train/epoch":3,"eval/runtime":4.4498,"eval/samples_per_second":112.366,"test/recall":0.946515397082658,"train/global_step":750,"_runtime":415,"test/loss":0.04531445354223251,"test/f1":0.9460043196544277,"eval/f1":0.9317875438123484,"_step":21,"total_flos":5.2571883657072e+14,"eval/recall":0.9365853658536586,"train_runtime":299.4505,"test/runtime":4.4802,"eval/precision":0.927038626609442,"test/samples_per_second":111.603,"train/grad_norm":1.0227235555648804,"eval/loss":0.09460805356502533,"_wandb":{"runtime":415},"_timestamp":1.763833407004338e+09,"train_loss":0.16440406481424968,"eval/accuracy":0.9788000720677437}

wandb_logs/run-20251122_173629-7f2wzkw5/logs/debug-core.log

@@ -0,0 +1,8 @@
+{"time":"2025-11-22T17:36:30.165217048Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpeym5nhp6/port-1459.txt","pid":1459,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2025-11-22T17:36:30.167187839Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1459-1649-3620678407/socket","Net":"unix"}}
+{"time":"2025-11-22T17:36:30.167304013Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1459}
+{"time":"2025-11-22T17:36:30.292606512Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2025-11-22T17:36:30.309708276Z","level":"INFO","msg":"handleInformInit: received","streamId":"7f2wzkw5","id":"1(@)"}
+{"time":"2025-11-22T17:36:30.659242282Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"7f2wzkw5","id":"1(@)"}
+{"time":"2025-11-22T17:43:28.79831427Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"7f2wzkw5","id":"1(@)"}
+{"time":"2025-11-22T17:43:28.803820639Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"7f2wzkw5","id":"1(@)"}

wandb_logs/run-20251122_173629-7f2wzkw5/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2025-11-22T17:36:30.309809744Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
+{"time":"2025-11-22T17:36:30.658933282Z","level":"INFO","msg":"stream: created new stream","id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659033035Z","level":"INFO","msg":"handler: started","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659231232Z","level":"INFO","msg":"stream: started","id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659288352Z","level":"INFO","msg":"writer: started","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:36:30.659315281Z","level":"INFO","msg":"sender: started","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.479276173Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-11-22T17:43:28.793500251Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-11-22T17:43:28.80038483Z","level":"INFO","msg":"stream: closing","id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.800412693Z","level":"INFO","msg":"handler: closed","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.800474018Z","level":"INFO","msg":"sender: closed","stream_id":"7f2wzkw5"}
+{"time":"2025-11-22T17:43:28.800494226Z","level":"INFO","msg":"stream: closed","id":"7f2wzkw5"}

wandb_logs/run-20251122_173629-7f2wzkw5/logs/debug.log

@@ -0,0 +1,29 @@
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Configure stats pid to 1459
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_173629-7f2wzkw5/logs/debug.log
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_173629-7f2wzkw5/logs/debug-internal.log
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:init():840] calling init triggers
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
+config: {'model': 'bert-base-multilingual-cased', 'train_file': 'synthetic_data_gen/data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
+2025-11-22 17:36:29,569 INFO    MainThread:1459 [wandb_init.py:init():888] starting backend
+2025-11-22 17:36:30,292 INFO    MainThread:1459 [wandb_init.py:init():891] sending inform_init request
+2025-11-22 17:36:30,301 INFO    MainThread:1459 [wandb_init.py:init():899] backend started and connected
+2025-11-22 17:36:30,304 INFO    MainThread:1459 [wandb_init.py:init():969] updated telemetry
+2025-11-22 17:36:30,311 INFO    MainThread:1459 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
+2025-11-22 17:36:31,052 INFO    MainThread:1459 [wandb_init.py:init():1040] starting run threads in backend
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_console_start():2504] atexit reg
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_redirect():2352] redirect: wrap_raw
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_redirect():2421] Wrapping output streams.
+2025-11-22 17:36:31,550 INFO    MainThread:1459 [wandb_run.py:_redirect():2444] Redirects installed.
+2025-11-22 17:36:31,556 INFO    MainThread:1459 [wandb_init.py:init():1080] run started, returning control to user process
+2025-11-22 17:36:55,547 INFO    MainThread:1459 [wandb_run.py:_config_callback():1385] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'float32', '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, 'architectures': ['BertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'O', 1: 'B-GUJ', 2: 'I-GUJ', 3: 'B-ENG', 4: 'I-ENG'}, 'label2id': {'O': 0, 'B-GUJ': 1, 'I-GUJ': 2, 'B-ENG': 3, 'I-ENG': 4}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, '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, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'bert-base-multilingual-cased', 'transformers_version': '4.57.1', 'directionality': 'bidi', 'model_type': 'bert', 'pooler_fc_size': 768, 'pooler_num_attention_heads': 12, 'pooler_num_fc_layers': 3, 'pooler_size_per_head': 128, 'pooler_type': 'first_token_transform', 'tf_legacy_loss': False, 'use_bfloat16': False, 'vocab_size': 119547, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_attentions': False, 'output_dir': './models/bert-multilingual-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/bert-multilingual-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': 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': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, '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, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', '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': 'h3110Fr13nd/guj-eng-code-switch-bert-multilingual-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-bert-multilingual-data2', '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, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2025-11-22 17:36:55,553 INFO    MainThread:1459 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 177266693 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7aae6e5964e0>>
+2025-11-22 17:36:55,553 INFO    MainThread:1459 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 177266693 None
+2025-11-22 17:43:27,008 INFO    MainThread:1459 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/7f2wzkw5
+2025-11-22 17:43:27,010 INFO    MainThread:1459 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
+2025-11-22 17:43:27,010 INFO    MainThread:1459 [wandb_run.py:_restore():2451] restore
+2025-11-22 17:43:27,011 INFO    MainThread:1459 [wandb_run.py:_restore():2457] restore done
+2025-11-22 17:43:28,797 INFO    MainThread:1459 [wandb_run.py:_footer_sync_info():3853] logging synced files

wandb_logs/run-20251122_173629-7f2wzkw5/run-7f2wzkw5.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1108f7f28b0bc33d05f8cabac53151ed68535bb4a475e0331182f2529307995a
+size 301613