Upload W&B logs

.gitattributes

@@ -34,3 +34,5 @@ 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
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+wandb_logs/run-20251116_132253-ytv0as6f/run-ytv0as6f.wandb filter=lfs diff=lfs merge=lfs -text
+wandb_logs/run-20251116_133532-vuimo2u7/run-vuimo2u7.wandb filter=lfs diff=lfs merge=lfs -text

wandb_logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2025-11-16T13:35:32.343727177Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
+{"time":"2025-11-16T13:35:32.543953023Z","level":"INFO","msg":"stream: created new stream","id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.544489786Z","level":"INFO","msg":"writer: started","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.54453477Z","level":"INFO","msg":"handler: started","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.544772028Z","level":"INFO","msg":"sender: started","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.544809026Z","level":"INFO","msg":"stream: started","id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.428356763Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-11-16T13:37:47.579481888Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-11-16T13:37:47.58406537Z","level":"INFO","msg":"stream: closing","id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.584085955Z","level":"INFO","msg":"handler: closed","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.584139239Z","level":"INFO","msg":"sender: closed","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.584148422Z","level":"INFO","msg":"stream: closed","id":"vuimo2u7"}

wandb_logs/debug.log

@@ -0,0 +1,29 @@
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Configure stats pid to 4984
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251116_133532-vuimo2u7/logs/debug.log
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251116_133532-vuimo2u7/logs/debug-internal.log
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:init():840] calling init triggers
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
+config: {'model': 'ai4bharat/indic-bert', 'train_file': 'data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:init():888] starting backend
+2025-11-16 13:35:32,337 INFO    MainThread:4984 [wandb_init.py:init():891] sending inform_init request
+2025-11-16 13:35:32,341 INFO    MainThread:4984 [wandb_init.py:init():899] backend started and connected
+2025-11-16 13:35:32,345 INFO    MainThread:4984 [wandb_init.py:init():969] updated telemetry
+2025-11-16 13:35:32,368 INFO    MainThread:4984 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
+2025-11-16 13:35:32,820 INFO    MainThread:4984 [wandb_init.py:init():1040] starting run threads in backend
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_console_start():2504] atexit reg
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_redirect():2352] redirect: wrap_raw
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_redirect():2421] Wrapping output streams.
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_redirect():2444] Redirects installed.
+2025-11-16 13:35:33,337 INFO    MainThread:4984 [wandb_init.py:init():1080] run started, returning control to user process
+2025-11-16 13:35:57,698 INFO    MainThread:4984 [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': None, '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': 2, 'pad_token_id': 0, 'eos_token_id': 3, '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': 'ai4bharat/indic-bert', 'transformers_version': '4.57.1', 'model_type': 'albert', 'net_structure_type': 0, 'gap_size': 0, 'num_memory_blocks': 0, 'down_scale_factor': 1, 'tf_legacy_loss': False, 'use_bfloat16': False, 'vocab_size': 200000, 'embedding_size': 128, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_hidden_groups': 1, 'num_attention_heads': 12, 'inner_group_num': 1, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0, 'attention_probs_dropout_prob': 0, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'classifier_dropout_prob': 0.1, 'position_embedding_type': 'absolute', 'output_attentions': False, 'output_dir': './models/indic-bert', '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/indic-bert/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-indic-bert', '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-indic-bert', '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}
+2025-11-16 13:35:57,704 INFO    MainThread:4984 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 32856837 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x151bdd652270>>
+2025-11-16 13:35:57,704 INFO    MainThread:4984 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 32856837 None
+2025-11-16 13:37:46,953 INFO    MainThread:4984 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/vuimo2u7
+2025-11-16 13:37:46,954 INFO    MainThread:4984 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
+2025-11-16 13:37:46,955 INFO    MainThread:4984 [wandb_run.py:_restore():2451] restore
+2025-11-16 13:37:46,955 INFO    MainThread:4984 [wandb_run.py:_restore():2457] restore done
+2025-11-16 13:37:47,583 INFO    MainThread:4984 [wandb_run.py:_footer_sync_info():3853] logging synced files

wandb_logs/run-20251116_132253-ytv0as6f/files/config.yaml

@@ -0,0 +1,543 @@
+_name_or_path:
+    value: bert-base-multilingual-cased
+_wandb:
+    value:
+        cli_version: 0.23.0
+        e:
+            pr4estv0wz5jnhtw0t3xa3ytx55z2f4h:
+                args:
+                    - configs/bert_multilingual.json
+                codePath: train.py
+                codePathLocal: train.py
+                cpu_count: 1
+                cpu_count_logical: 2
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "120942624768"
+                        used: "41795239936"
+                email: vijaysinghkushwaha3737@gmail.com
+                executable: /usr/bin/python3
+                git:
+                    commit: 49a00e4673c8e2994ddcb718dde864a99cc0961f
+                    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-6248e46d-a025-808c-15ca-20242f9a252c
+                host: 140cf68b228a
+                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: "2025-11-16T13:22:53.364880Z"
+                writerId: pr4estv0wz5jnhtw0t3xa3ytx55z2f4h
+        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
+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/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
+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
+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: 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-20251116_132253-ytv0as6f/files/output.log

@@ -0,0 +1,83 @@
+
+    _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|
+    _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|
+    _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|
+    _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|
+    _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|
+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, 212kB/s]
+config.json: 100% 625/625 [00:00<00:00, 2.82MB/s]
+vocab.txt: 100% 996k/996k [00:00<00:00, 7.75MB/s]
+tokenizer.json: 100% 1.96M/1.96M [00:00<00:00, 7.37MB/s]
+model.safetensors: 100% 714M/714M [00:06<00:00, 116MB/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, 10.9MB/s]
+{'loss': 1.6561, 'grad_norm': 11.050471305847168, 'learning_rate': 0.0, 'epoch': 0.01}
+{'loss': 1.0255, 'grad_norm': 7.669041633605957, 'learning_rate': 1.9600000000000002e-05, 'epoch': 0.3}
+{'loss': 0.2894, 'grad_norm': 2.569448947906494, 'learning_rate': 1.7782805429864253e-05, 'epoch': 0.61}
+{'loss': 0.1821, 'grad_norm': 2.593822956085205, 'learning_rate': 1.552036199095023e-05, 'epoch': 0.91}
+Downloading builder script: 6.34kB [00:00, 9.53MB/s]
+100% 492/492 [05:03<00:00,  1.62it/s]:00, ?B/s]
+{'eval_loss': 0.07226230204105377, 'eval_precision': 0.8930976430976431, 'eval_recall': 0.9068376068376068, 'eval_f1': 0.8999151823579304, 'eval_accuracy': 0.9802466756600501, 'eval_runtime': 3.0714, 'eval_samples_per_second': 106.14, 'eval_steps_per_second': 3.581, 'epoch': 1.0}
+{'loss': 0.1071, 'grad_norm': 1.1867393255233765, 'learning_rate': 1.32579185520362e-05, 'epoch': 1.22}
+{'loss': 0.1027, 'grad_norm': 1.172904133796692, 'learning_rate': 1.0995475113122173e-05, 'epoch': 1.52}
+{'loss': 0.0789, 'grad_norm': 3.011417865753174, 'learning_rate': 8.733031674208145e-06, 'epoch': 1.83}
+Processing Files (3 / 3)      : 100% 709M/709M [00:10<00:00, 70.8MB/s, 72.4MB/s  ] 
+{'eval_loss': 0.04031597822904587, 'eval_precision': 0.935374149659864, 'eval_recall': 0.9401709401709402, 'eval_f1': 0.937766410912191, 'eval_accuracy': 0.9896897282713433, 'eval_runtime': 2.7806, 'eval_samples_per_second': 117.243, 'eval_steps_per_second': 3.956, 'epoch': 2.0}
+{'loss': 0.0632, 'grad_norm': 1.8443704843521118, 'learning_rate': 6.470588235294119e-06, 'epoch': 2.13}
+{'loss': 0.0463, 'grad_norm': 1.2871953248977661, 'learning_rate': 4.208144796380091e-06, 'epoch': 2.44}
+{'loss': 0.054, 'grad_norm': 2.695483684539795, 'learning_rate': 1.9457013574660634e-06, 'epoch': 2.74}
+{'eval_loss': 0.04117187485098839, 'eval_precision': 0.9366980325064157, 'eval_recall': 0.9358974358974359, 'eval_f1': 0.9362975630611372, 'eval_accuracy': 0.9890152245133937, 'eval_runtime': 2.8999, 'eval_samples_per_second': 112.418, 'eval_steps_per_second': 3.793, 'epoch': 3.0}
+{'train_runtime': 303.4576, 'train_samples_per_second': 25.793, 'train_steps_per_second': 1.621, 'train_loss': 0.20365032820197626, 'epoch': 3.0}
+New Data Upload               : 100% 709M/709M [00:10<00:00, 70.8MB/s, 72.4MB/s  ] 
+  ...lingual/model.safetensors: 100% 709M/709M [00:08<00:00, 80.5MB/s] 
+  ...99406.140cf68b228a.1342.0: 100% 9.31k/9.31k [00:01<00:00, 4.64kB/s]
+  ...lingual/training_args.bin: 100% 5.91k/5.91k [00:01<00:00, 2.95kB/s]
+Processing Files (3 / 3)      : 100% 709M/709M [00:04<00:00, 154MB/s,  152MB/s  ] 
+New Data Upload               : |          |  0.00B /  0.00B,  0.00B/s  
+  ...lingual/training_args.bin: 100% 5.91k/5.91k [00:04<?, ?B/s]
+  ...99406.140cf68b228a.1342.0: 100% 9.31k/9.31k [00:04<?, ?B/s]
+  ...lingual/model.safetensors: 100% 709M/709M [00:04<00:00, 152MB/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               =   320193GF
+  train_loss               =     0.2037
+  train_runtime            = 0:05:03.45
+  train_samples_per_second =     25.793
+  train_steps_per_second   =      1.621
+100% 11/11 [00:02<00:00,  4.79it/s]
+***** eval metrics *****
+  epoch                   =        3.0
+  eval_accuracy           =     0.9897
+  eval_f1                 =     0.9378
+  eval_loss               =     0.0403
+  eval_precision          =     0.9354
+  eval_recall             =     0.9402
+  eval_runtime            = 0:00:02.44
+  eval_samples_per_second =    133.332
+  eval_steps_per_second   =      4.499
+ 91% 10/11 [00:01<00:00,  6.22it/s]early stopping required metric_for_best_model, but did not find eval_f1 so early stopping is disabled
+100% 11/11 [00:02<00:00,  4.46it/s]
+***** test metrics *****
+  epoch                   =        3.0
+  test_accuracy           =     0.9742
+  test_f1                 =     0.9105
+  test_loss               =     0.0997
+  test_precision          =      0.909
+  test_recall             =      0.912
+  test_runtime            = 0:00:02.63
+  test_samples_per_second =     124.06
+  test_steps_per_second   =      4.173

wandb_logs/run-20251116_132253-ytv0as6f/files/requirements.txt

@@ -0,0 +1,700 @@
+types-setuptools==80.9.0.20250822
+setuptools==75.2.0
+pip==24.1.2
+requirements-parser==0.9.0
+pandas==2.3.3
+tensorboard==2.20.0
+ipykernel==7.1.0
+seqeval==1.2.2
+google-genai==1.50.1
+widgetsnbextension==4.0.15
+evaluate==0.4.6
+jedi==0.19.2
+pyarrow==22.0.0
+datasets==4.4.1
+numpy==2.3.4
+scikit-learn==1.7.2
+wandb==0.23.0
+jupyter_client==8.6.3
+comm==0.2.3
+ipywidgets==8.1.8
+google-colab==1.0.0
+yfinance==0.2.66
+pytensor==2.35.1
+dask==2025.9.1
+ipython-sql==0.5.0
+libucxx-cu12==0.46.0
+duckdb==1.3.2
+h5py==3.15.1
+requests==2.32.4
+db-dtypes==1.4.4
+xyzservices==2025.10.0
+bigframes==2.28.0
+grpclib==0.4.8
+httpcore==1.0.9
+cudf-polars-cu12==25.10.0
+webcolors==25.10.0
+cvxopt==1.3.2
+google-cloud-bigquery-storage==2.34.0
+future==1.0.0
+nvidia-cuda-cccl-cu12==12.9.27
+tf_keras==2.19.0
+hf_transfer==0.1.9
+simple-parsing==0.1.7
+arviz==0.22.0
+opentelemetry-semantic-conventions==0.58b0
+click==8.3.0
+locket==1.0.0
+libpysal==4.13.0
+rsa==4.9.1
+distro==1.9.0
+nx-cugraph-cu12==25.10.0
+smmap==5.0.2
+google-auth-oauthlib==1.2.3
+tzlocal==5.3.1
+ipyfilechooser==0.6.0
+googledrivedownloader==1.1.0
+nvidia-cusparse-cu12==12.5.4.2
+jax-cuda12-plugin==0.7.2
+httpx-sse==0.4.3
+google-crc32c==1.7.1
+matplotlib==3.10.0
+pyomo==6.9.5
+jsonpatch==1.33
+jupyter-console==6.6.3
+Flask==3.1.2
+nibabel==5.3.2
+anyio==4.11.0
+matplotlib-venn==1.1.2
+pydantic_core==2.33.2
+fasttransform==0.0.2
+sortedcontainers==2.4.0
+astropy-iers-data==0.2025.11.10.0.38.31
+semantic-version==2.10.0
+preshed==3.0.10
+nbconvert==7.16.6
+pluggy==1.6.0
+wcwidth==0.2.14
+overrides==7.7.0
+sklearn-pandas==2.2.0
+google-cloud-functions==1.21.0
+sphinxcontrib-jsmath==1.0.1
+html5lib==1.1
+linkify-it-py==2.0.3
+ruff==0.14.4
+google-api-core==2.28.1
+pooch==1.8.2
+google-auth==2.38.0
+jsonpointer==3.0.0
+google-cloud-speech==2.34.0
+argon2-cffi==25.1.0
+orjson==3.11.4
+wheel==0.45.1
+typing_extensions==4.15.0
+uritemplate==4.2.0
+portpicker==1.5.2
+zipp==3.23.0
+cuda-python==12.9.4
+numexpr==2.14.1
+networkx==3.5
+progressbar2==4.5.0
+dm-tree==0.1.9
+ibis-framework==9.5.0
+jaraco.context==6.0.1
+threadpoolctl==3.6.0
+libkvikio-cu12==25.10.0
+betterproto==2.0.0b6
+pydantic-settings==2.12.0
+grpcio==1.76.0
+pyOpenSSL==24.2.1
+logical-unification==0.4.7
+nvidia-cusparselt-cu12==0.7.1
+folium==0.20.0
+stanio==0.5.1
+grpc-google-iam-v1==0.14.3
+ply==3.11
+confection==0.1.5
+httpx==0.28.1
+ffmpy==1.0.0
+gradio_client==1.13.3
+pandas-stubs==2.2.2.240909
+inflect==7.5.0
+osqp==1.0.5
+filelock==3.20.0
+lazy_loader==0.4
+toml==0.10.2
+audioread==3.1.0
+stringzilla==4.2.3
+nvidia-nvtx-cu12==12.6.77
+wordcloud==1.9.4
+rfc3986-validator==0.1.1
+blinker==1.9.0
+iniconfig==2.3.0
+sphinxcontrib-qthelp==2.0.0
+holidays==0.84
+tensorboard-data-server==0.7.2
+smart_open==7.5.0
+decorator==4.4.2
+plotnine==0.14.5
+omegaconf==2.3.0
+numba-cuda==0.19.1
+ipytree==0.2.2
+moviepy==1.0.3
+traitlets==5.7.1
+cuml-cu12==25.10.0
+debugpy==1.8.15
+PyJWT==2.10.1
+fonttools==4.60.1
+tensorflow-datasets==4.9.9
+absl-py==1.4.0
+etils==1.13.0
+ml_dtypes==0.5.3
+idna==3.11
+google-cloud-appengine-logging==1.7.0
+bokeh==3.7.3
+text-unidecode==1.3
+blis==1.3.0
+llvmlite==0.43.0
+multitasking==0.0.12
+msgpack==1.1.2
+tensorflow-text==2.19.0
+rfc3339-validator==0.1.4
+keras-hub==0.21.1
+jupyterlab_pygments==0.3.0
+yarl==1.22.0
+ipyevents==2.0.4
+xgboost==3.1.1
+zict==3.0.0
+torchtune==0.6.1
+spanner-graph-notebook==1.1.8
+patsy==1.0.2
+mizani==0.13.5
+fastcore==1.8.16
+et_xmlfile==2.0.0
+jeepney==0.9.0
+geopandas==1.1.1
+tinycss2==1.4.0
+backcall==0.2.0
+jiter==0.12.0
+flax==0.10.7
+PySocks==1.7.1
+Pygments==2.19.2
+hpack==4.1.0
+pytz==2025.2
+narwhals==2.11.0
+murmurhash==1.0.13
+slicer==0.0.8
+google-cloud-bigtable==2.34.0
+cmake==3.31.6
+antlr4-python3-runtime==4.9.3
+Jinja2==3.1.6
+python-slugify==8.0.4
+multiprocess==0.70.16
+gitdb==4.0.12
+proglog==0.1.12
+psygnal==0.15.0
+geographiclib==2.1
+jupyter_server==2.14.0
+requests-oauthlib==2.0.0
+plotly==5.24.1
+raft-dask-cu12==25.10.0
+torchao==0.10.0
+opencv-contrib-python==4.12.0.88
+dlib==19.24.6
+cuda-toolkit==12.9.1
+thinc==8.3.8
+Bottleneck==1.4.2
+regex==2024.11.6
+google-cloud-language==2.18.0
+cymem==2.0.11
+Authlib==1.6.5
+pyperclip==1.11.0
+ratelim==0.1.6
+mpmath==1.3.0
+astunparse==1.6.3
+missingno==0.5.2
+cmdstanpy==1.3.0
+tensorstore==0.1.78
+typeguard==4.4.4
+keras==3.10.0
+toolz==0.12.1
+nltk==3.9.1
+aiofiles==24.1.0
+albucore==0.0.24
+pycryptodomex==3.23.0
+pydantic==2.11.10
+websocket-client==1.9.0
+frozenlist==1.8.0
+glob2==0.7
+libraft-cu12==25.10.0
+tornado==6.5.1
+tweepy==4.16.0
+babel==2.17.0
+treelite==4.4.1
+librmm-cu12==25.10.0
+soxr==1.0.0
+xlrd==2.0.2
+tabulate==0.9.0
+PyYAML==6.0.3
+imageio-ffmpeg==0.6.0
+pyzmq==26.2.1
+webencodings==0.5.1
+tzdata==2025.2
+pickleshare==0.7.5
+opentelemetry-api==1.37.0
+chardet==5.2.0
+ptyprocess==0.7.0
+optree==0.17.0
+flatbuffers==25.9.23
+jsonpickle==4.1.1
+cramjam==2.11.0
+tables==3.10.2
+tf-slim==1.1.0
+fastai==2.8.5
+cloudpickle==3.1.2
+orbax-checkpoint==0.11.28
+soundfile==0.13.1
+highspy==1.12.0
+pexpect==4.9.0
+nbformat==5.10.4
+atpublic==5.1
+python-box==7.3.2
+miniKanren==1.0.5
+nbclient==0.10.2
+nvidia-cuda-runtime-cu12==12.6.77
+arrow==1.4.0
+dopamine_rl==4.1.2
+cuda-pathfinder==1.3.2
+google-cloud-core==2.5.0
+gspread==6.2.1
+PyOpenGL==3.1.10
+google==2.0.3
+fastjsonschema==2.21.2
+google-cloud-resource-manager==1.15.0
+mistune==3.1.4
+absolufy-imports==0.3.1
+annotated-doc==0.0.4
+scs==3.2.9
+kagglehub==0.3.13
+dask-cuda==25.10.0
+dill==0.3.8
+spacy==3.8.8
+tensorflow-metadata==1.17.2
+oauth2client==4.1.3
+rich==13.9.4
+python-dateutil==2.9.0.post0
+aiohttp==3.13.2
+tensorflow==2.19.0
+ipyparallel==8.8.0
+scikit-image==0.25.2
+anywidget==0.9.19
+etuples==0.3.10
+bqplot==0.12.45
+lightgbm==4.6.0
+opentelemetry-exporter-otlp-proto-http==1.37.0
+argon2-cffi-bindings==25.1.0
+libcuml-cu12==25.10.0
+tensorflow-hub==0.16.1
+branca==0.8.2
+google-auth-httplib2==0.2.1
+cryptography==43.0.3
+python-dotenv==1.2.1
+ImageIO==2.37.2
+aiohappyeyeballs==2.6.1
+ale-py==0.11.2
+httplib2==0.31.0
+jupyter-leaflet==0.20.0
+jupyter_core==5.9.1
+gspread-dataframe==4.0.0
+music21==9.3.0
+spacy-legacy==3.0.12
+gym==0.25.2
+traittypes==0.2.3
+nvidia-nccl-cu12==2.27.3
+altair==5.5.0
+tblib==3.2.1
+langchain==0.3.27
+pyspark==3.5.1
+optax==0.2.6
+build==1.3.0
+hyperopt==0.2.7
+google-cloud-trace==1.17.0
+sphinxcontrib-htmlhelp==2.1.0
+google-cloud-spanner==3.59.0
+cycler==0.12.1
+namex==0.1.0
+pymc==5.26.1
+Cython==3.0.12
+tensorflow-probability==0.25.0
+nvidia-cublas-cu12==12.6.4.1
+pylibcugraph-cu12==25.10.1
+beartype==0.22.5
+srsly==2.5.1
+lark==1.3.1
+h11==0.16.0
+grpc-interceptor==0.15.4
+psutil==5.9.5
+peewee==3.18.3
+nvidia-cuda-nvcc-cu12==12.9.86
+prompt_toolkit==3.0.52
+distributed-ucxx-cu12==0.46.0
+gymnasium==1.2.2
+gym-notices==0.1.0
+pandas-gbq==0.30.0
+ipython==7.34.0
+pycocotools==2.0.10
+uri-template==1.3.0
+earthengine-api==1.5.24
+jieba==0.42.1
+cloudpathlib==0.23.0
+markdown-it-py==4.0.0
+prettytable==3.16.0
+fastprogress==1.0.3
+parso==0.8.5
+prometheus_client==0.23.1
+google-pasta==0.2.0
+py-cpuinfo==9.0.0
+Mako==1.3.10
+distributed==2025.9.1
+grpcio-status==1.71.2
+wasabi==1.1.3
+google-cloud-secret-manager==2.25.0
+urllib3==2.5.0
+packaging==25.0
+python-louvain==0.16
+simplejson==3.20.2
+param==2.2.1
+sphinxcontrib-serializinghtml==2.0.0
+pyparsing==3.2.5
+Markdown==3.10
+alembic==1.17.1
+GDAL==3.8.4
+timm==1.0.22
+google-cloud-bigquery==3.38.0
+openpyxl==3.1.5
+tenacity==8.5.0
+bigquery-magics==0.10.3
+blobfile==3.1.0
+pygit2==1.19.0
+imbalanced-learn==0.14.0
+opentelemetry-exporter-gcp-monitoring==1.11.0a0
+termcolor==3.2.0
+pydot==3.0.4
+sse-starlette==3.0.3
+spacy-loggers==1.0.5
+rpds-py==0.28.0
+watchdog==6.0.0
+sentencepiece==0.2.1
+stumpy==1.13.0
+statsmodels==0.14.5
+google-adk==1.17.0
+isoduration==20.11.0
+community==1.0.0b1
+pillow==11.3.0
+alabaster==1.0.0
+contourpy==1.3.3
+google-cloud-datastore==2.21.0
+jax==0.7.2
+bleach==6.3.0
+panel==1.8.3
+attrs==25.4.0
+CacheControl==0.14.3
+mlxtend==0.23.4
+intel-openmp==2025.3.1
+umf==1.0.2
+google-cloud-translate==3.23.0
+google-cloud-storage==2.19.0
+nvidia-nvjitlink-cu12==12.6.85
+jsonschema==4.25.1
+python-snappy==0.7.3
+typer==0.20.0
+roman-numerals-py==3.1.0
+opentelemetry-exporter-gcp-trace==1.11.0
+pyproj==3.7.2
+opencv-python-headless==4.12.0.88
+google-resumable-media==2.7.2
+opentelemetry-proto==1.37.0
+chex==0.1.90
+geocoder==1.38.1
+fastapi==0.121.1
+beautifulsoup4==4.13.5
+textblob==0.19.0
+accelerate==1.11.0
+defusedxml==0.7.1
+jaraco.classes==3.4.0
+uc-micro-py==1.0.3
+curl_cffi==0.13.0
+hdbscan==0.8.40
+pydotplus==2.0.2
+pynndescent==0.5.13
+colour==0.1.5
+google-cloud-monitoring==2.28.0
+tensorflow_decision_forests==1.12.0
+einops==0.8.1
+rmm-cu12==25.10.0
+snowballstemmer==3.0.1
+jupyter_kernel_gateway==2.5.2
+groovy==0.1.2
+blosc2==3.11.0
+h5netcdf==1.7.3
+nvidia-cuda-nvrtc-cu12==12.6.77
+pyerfa==2.0.1.5
+psycopg2==2.9.11
+docutils==0.21.2
+google-ai-generativelanguage==0.6.15
+prophet==1.1.7
+pyviz_comms==3.0.6
+albumentations==2.0.8
+easydict==1.13
+Send2Trash==1.8.3
+rapids-logger==0.1.19
+mdurl==0.1.2
+frozendict==2.4.6
+nvidia-cufft-cu12==11.3.0.4
+sqlparse==0.5.3
+torchaudio==2.8.0+cu126
+simsimd==6.5.3
+nvidia-ml-py==13.580.82
+sentry-sdk==2.44.0
+nbclassic==1.3.3
+ydf==0.13.0
+nvidia-cusolver-cu12==11.7.1.2
+langchain-text-splitters==0.3.11
+numba==0.60.0
+PyGObject==3.42.0
+holoviews==1.22.0
+jupyterlab_widgets==3.0.16
+pycparser==2.23
+mkl==2025.2.0
+jupyter_server_terminals==0.5.3
+brotli==1.2.0
+promise==2.3
+ipyleaflet==0.20.0
+weasel==0.4.2
+httpimport==1.4.1
+nvidia-cudnn-cu12==9.10.2.21
+SQLAlchemy==2.0.44
+cons==0.4.7
+wrapt==2.0.1
+openai==1.109.1
+charset-normalizer==3.4.4
+peft==0.17.1
+gin-config==0.5.0
+shellingham==1.5.4
+soupsieve==2.8
+yellowbrick==1.5
+en_core_web_sm==3.8.0
+fsspec==2025.3.0
+google-cloud-firestore==2.21.0
+google-cloud-audit-log==0.4.0
+nvidia-cufile-cu12==1.11.1.6
+triton==3.4.0
+mdit-py-plugins==0.5.0
+platformdirs==4.5.0
+nest-asyncio==1.6.0
+hyperframe==6.1.0
+libucx-cu12==1.19.0
+docstring_parser==0.17.0
+nvtx==0.2.13
+cufflinks==0.17.3
+rpy2==3.5.17
+torchsummary==1.5.1
+eerepr==0.1.2
+array_record==0.8.2
+cvxpy==1.6.7
+opentelemetry-exporter-gcp-logging==1.11.0a0
+typing-inspection==0.4.2
+ucxx-cu12==0.46.0
+gradio==5.49.1
+types-pytz==2025.2.0.20251108
+safehttpx==0.1.7
+safetensors==0.6.2
+opentelemetry-resourcedetector-gcp==1.11.0a0
+aiosignal==1.4.0
+librosa==0.11.0
+websockets==15.0.1
+opt_einsum==3.4.0
+clarabel==0.11.1
+pyshp==3.0.2.post1
+sqlglot==25.20.2
+fastrlock==0.8.3
+kiwisolver==1.4.9
+google-api-python-client==2.187.0
+uvicorn==0.38.0
+scooby==0.11.0
+shap==0.50.0
+keyring==25.6.0
+opencv-python==4.12.0.88
+typer-slim==0.20.0
+terminado==0.18.1
+protobuf==5.29.5
+google-cloud-dataproc==5.23.0
+pytest==8.4.2
+pandas-datareader==0.10.0
+pylibcudf-cu12==25.10.0
+opentelemetry-exporter-otlp-proto-common==1.37.0
+mcp==1.21.0
+diffusers==0.35.2
+tiktoken==0.12.0
+opentelemetry-sdk==1.37.0
+SecretStorage==3.4.1
+colorlover==0.3.0
+nvidia-curand-cu12==10.3.7.77
+libcudf-cu12==25.10.0
+geopy==2.4.1
+torchdata==0.11.0
+geemap==0.35.3
+Sphinx==8.2.3
+proto-plus==1.26.1
+graphviz==0.21
+wurlitzer==3.1.1
+kaggle==1.7.4.5
+firebase-admin==6.9.0
+shapely==2.1.2
+astropy==7.1.1
+zstandard==0.25.0
+torch==2.8.0+cu126
+polars==1.31.0
+tokenizers==0.22.1
+ipython-genutils==0.2.0
+python-utils==3.9.1
+python-multipart==0.0.20
+vega-datasets==0.9.0
+treescope==0.1.10
+sniffio==1.3.1
+fqdn==1.5.1
+google-cloud-bigquery-connection==1.19.0
+jax-cuda12-pjrt==0.7.2
+editdistance==0.8.1
+multidict==6.7.0
+PyWavelets==1.9.0
+pydata-google-auth==1.9.1
+importlib_resources==6.5.2
+intel-cmplr-lib-ur==2025.3.1
+sphinxcontrib-applehelp==2.0.0
+fastdownload==0.0.7
+autograd==1.8.0
+tqdm==4.67.1
+notebook==6.5.7
+greenlet==3.2.4
+xxhash==3.6.0
+immutabledict==4.2.2
+sentence-transformers==5.1.2
+imutils==0.5.4
+umap-learn==0.5.9.post2
+tbb==2022.3.0
+python-json-logger==4.0.0
+matplotlib-inline==0.2.1
+joblib==1.5.2
+pycairo==1.29.0
+gcsfs==2025.3.0
+huggingface-hub==0.36.0
+google-generativeai==0.8.5
+imagesize==1.4.1
+langchain-core==0.3.79
+hf-xet==1.2.0
+pygame==2.6.1
+gdown==5.2.0
+dataproc-spark-connect==0.8.3
+transformers==4.57.1
+multipledispatch==1.0.0
+jaraco.functools==4.3.0
+colorcet==3.1.0
+tomlkit==0.13.3
+notebook_shim==0.2.4
+keyrings.google-artifactregistry-auth==1.1.2
+xarray==2025.10.1
+six==1.17.0
+jaxlib==0.7.2
+google-cloud-aiplatform==1.126.1
+certifi==2025.10.5
+catalogue==2.0.10
+humanize==4.14.0
+parsy==2.2
+cuda-bindings==12.9.4
+rfc3987-syntax==1.1.0
+propcache==0.4.1
+cachetools==5.5.2
+google-cloud-logging==3.12.1
+cffi==2.0.0
+googleapis-common-protos==1.72.0
+tcmlib==1.4.1
+cuda-core==0.3.2
+py4j==0.10.9.7
+pyogrio==0.11.1
+requests-toolbelt==1.0.0
+seaborn==0.13.2
+sphinxcontrib-devhelp==2.0.0
+referencing==0.37.0
+pylibraft-cu12==25.10.0
+more-itertools==10.8.0
+entrypoints==0.4
+keras-nlp==0.21.1
+libcugraph-cu12==25.10.1
+sympy==1.13.3
+PyDrive2==1.21.3
+natsort==8.4.0
+cupy-cuda12x==13.6.0
+h2==4.3.0
+jupyter-events==0.12.0
+google-cloud-discoveryengine==0.13.12
+itsdangerous==2.2.0
+pydub==0.25.1
+nvidia-nvshmem-cu12==3.4.5
+sqlalchemy-spanner==1.17.1
+gast==0.6.0
+partd==1.4.2
+pyasn1_modules==0.4.2
+dask-cudf-cu12==25.10.0
+cudf-cu12==25.10.0
+plum-dispatch==2.6.0
+pyasn1==0.6.1
+pandocfilters==1.5.1
+libclang==18.1.1
+xarray-einstats==0.9.1
+nvidia-cuda-cupti-cu12==12.6.80
+torchvision==0.23.0+cu126
+GitPython==3.1.45
+oauthlib==3.3.1
+cyipopt==1.5.0
+MarkupSafe==3.0.3
+langsmith==0.4.42
+starlette==0.49.3
+Farama-Notifications==0.0.4
+lxml==5.4.0
+jsonschema-specifications==2025.9.1
+jupytext==1.17.3
+scipy==1.16.3
+tifffile==2025.10.16
+tsfresh==0.21.1
+importlib_metadata==8.7.0
+annotated-types==0.7.0
+pyproject_hooks==1.2.0
+Werkzeug==3.1.3
+ndindex==1.10.0
+rapids-dask-dependency==25.10.0
+python-apt==0.0.0
+pyparsing==2.4.7
+SecretStorage==3.3.1
+more-itertools==8.10.0
+cryptography==3.4.8
+six==1.16.0
+blinker==1.4
+httplib2==0.20.2
+keyring==23.5.0
+lazr.restfulclient==0.14.4
+PyGObject==3.42.1
+PyJWT==2.3.0
+importlib-metadata==4.6.4
+wadllib==1.3.6
+dbus-python==1.2.18
+oauthlib==3.2.0
+lazr.uri==1.0.6
+jeepney==0.7.1
+zipp==1.0.0
+distro==1.7.0
+launchpadlib==1.10.16
+python-apt==2.4.0+ubuntu4
+Mako==1.1.3
+Markdown==3.3.6
+MarkupSafe==2.0.1

wandb_logs/run-20251116_132253-ytv0as6f/files/wandb-metadata.json

@@ -0,0 +1,43 @@
+{
+  "os": "Linux-6.6.105+-x86_64-with-glibc2.35",
+  "python": "CPython 3.12.12",
+  "startedAt": "2025-11-16T13:22:53.364880Z",
+  "args": [
+    "configs/bert_multilingual.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": "49a00e4673c8e2994ddcb718dde864a99cc0961f"
+  },
+  "email": "vijaysinghkushwaha3737@gmail.com",
+  "root": "/content/code-switch-identification-model",
+  "host": "140cf68b228a",
+  "executable": "/usr/bin/python3",
+  "cpu_count": 1,
+  "cpu_count_logical": 2,
+  "gpu": "Tesla T4",
+  "gpu_count": 1,
+  "disk": {
+    "/": {
+      "total": "120942624768",
+      "used": "41795239936"
+    }
+  },
+  "memory": {
+    "total": "13605851136"
+  },
+  "gpu_nvidia": [
+    {
+      "name": "Tesla T4",
+      "memoryTotal": "16106127360",
+      "cudaCores": 2560,
+      "architecture": "Turing",
+      "uuid": "GPU-6248e46d-a025-808c-15ca-20242f9a252c"
+    }
+  ],
+  "cudaVersion": "12.4",
+  "writerId": "pr4estv0wz5jnhtw0t3xa3ytx55z2f4h"
+}

wandb_logs/run-20251116_132253-ytv0as6f/files/wandb-summary.json

@@ -0,0 +1 @@
+{"total_flos":3.4380491858271e+14,"eval/f1":0.937766410912191,"train/epoch":3,"eval/steps_per_second":4.499,"test/recall":0.9119804400977995,"eval/loss":0.04031597822904587,"train/learning_rate":1.9457013574660634e-06,"test/runtime":2.6358,"test/steps_per_second":4.173,"train_runtime":303.4576,"train_steps_per_second":1.621,"train_samples_per_second":25.793,"eval/recall":0.9401709401709402,"test/precision":0.909017059301381,"_step":15,"eval/precision":0.935374149659864,"test/samples_per_second":124.06,"_runtime":480,"eval/accuracy":0.9896897282713433,"train/grad_norm":2.695483684539795,"_wandb":{"runtime":480},"_timestamp":1.7632998546177845e+09,"test/loss":0.0997130274772644,"eval/runtime":2.445,"eval/samples_per_second":133.332,"train/global_step":492,"test/accuracy":0.9741929516233466,"train/loss":0.054,"test/f1":0.9104963384865745,"train_loss":0.20365032820197626}

wandb_logs/run-20251116_132253-ytv0as6f/logs/debug-core.log

@@ -0,0 +1,16 @@
+{"time":"2025-11-16T13:22:53.707632662Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpl7qq4q77/port-1342.txt","pid":1342,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2025-11-16T13:22:53.708165618Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1342}
+{"time":"2025-11-16T13:22:53.708167179Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1342-1726-1332617147/socket","Net":"unix"}}
+{"time":"2025-11-16T13:22:53.892852017Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2025-11-16T13:22:53.902787629Z","level":"INFO","msg":"handleInformInit: received","streamId":"ytv0as6f","id":"1(@)"}
+{"time":"2025-11-16T13:22:54.08348205Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ytv0as6f","id":"1(@)"}
+{"time":"2025-11-16T13:30:55.241037221Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"ytv0as6f","id":"1(@)"}
+{"time":"2025-11-16T13:30:55.246920479Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"ytv0as6f","id":"1(@)"}
+{"time":"2025-11-16T13:30:59.276292259Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
+{"time":"2025-11-16T13:30:59.276340475Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
+{"time":"2025-11-16T13:30:59.276350632Z","level":"INFO","msg":"server is shutting down"}
+{"time":"2025-11-16T13:30:59.276416691Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1342-1726-1332617147/socket","Net":"unix"}}
+{"time":"2025-11-16T13:30:59.276454208Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
+{"time":"2025-11-16T13:30:59.276505926Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
+{"time":"2025-11-16T13:30:59.276512722Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
+{"time":"2025-11-16T13:30:59.276519022Z","level":"INFO","msg":"server is closed"}

wandb_logs/run-20251116_132253-ytv0as6f/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2025-11-16T13:22:53.902909723Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
+{"time":"2025-11-16T13:22:54.083264621Z","level":"INFO","msg":"stream: created new stream","id":"ytv0as6f"}
+{"time":"2025-11-16T13:22:54.083470919Z","level":"INFO","msg":"stream: started","id":"ytv0as6f"}
+{"time":"2025-11-16T13:22:54.086792761Z","level":"INFO","msg":"handler: started","stream_id":"ytv0as6f"}
+{"time":"2025-11-16T13:22:54.086939017Z","level":"INFO","msg":"sender: started","stream_id":"ytv0as6f"}
+{"time":"2025-11-16T13:22:54.087261245Z","level":"INFO","msg":"writer: started","stream_id":"ytv0as6f"}
+{"time":"2025-11-16T13:30:55.110413885Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-11-16T13:30:55.23681691Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-11-16T13:30:55.243025488Z","level":"INFO","msg":"stream: closing","id":"ytv0as6f"}
+{"time":"2025-11-16T13:30:55.243059028Z","level":"INFO","msg":"handler: closed","stream_id":"ytv0as6f"}
+{"time":"2025-11-16T13:30:55.243113845Z","level":"INFO","msg":"sender: closed","stream_id":"ytv0as6f"}
+{"time":"2025-11-16T13:30:55.243125538Z","level":"INFO","msg":"stream: closed","id":"ytv0as6f"}

wandb_logs/run-20251116_132253-ytv0as6f/logs/debug.log

@@ -0,0 +1,29 @@
+2025-11-16 13:22:53,366 INFO    MainThread:1342 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
+2025-11-16 13:22:53,366 INFO    MainThread:1342 [wandb_setup.py:_flush():80] Configure stats pid to 1342
+2025-11-16 13:22:53,366 INFO    MainThread:1342 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-11-16 13:22:53,366 INFO    MainThread:1342 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
+2025-11-16 13:22:53,366 INFO    MainThread:1342 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-11-16 13:22:53,367 INFO    MainThread:1342 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251116_132253-ytv0as6f/logs/debug.log
+2025-11-16 13:22:53,367 INFO    MainThread:1342 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251116_132253-ytv0as6f/logs/debug-internal.log
+2025-11-16 13:22:53,367 INFO    MainThread:1342 [wandb_init.py:init():840] calling init triggers
+2025-11-16 13:22:53,367 INFO    MainThread:1342 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
+config: {'model': 'bert-base-multilingual-cased', 'train_file': 'data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
+2025-11-16 13:22:53,367 INFO    MainThread:1342 [wandb_init.py:init():888] starting backend
+2025-11-16 13:22:53,893 INFO    MainThread:1342 [wandb_init.py:init():891] sending inform_init request
+2025-11-16 13:22:53,900 INFO    MainThread:1342 [wandb_init.py:init():899] backend started and connected
+2025-11-16 13:22:53,904 INFO    MainThread:1342 [wandb_init.py:init():969] updated telemetry
+2025-11-16 13:22:53,910 INFO    MainThread:1342 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
+2025-11-16 13:22:54,248 INFO    MainThread:1342 [wandb_init.py:init():1040] starting run threads in backend
+2025-11-16 13:22:54,737 INFO    MainThread:1342 [wandb_run.py:_console_start():2504] atexit reg
+2025-11-16 13:22:54,737 INFO    MainThread:1342 [wandb_run.py:_redirect():2352] redirect: wrap_raw
+2025-11-16 13:22:54,737 INFO    MainThread:1342 [wandb_run.py:_redirect():2421] Wrapping output streams.
+2025-11-16 13:22:54,738 INFO    MainThread:1342 [wandb_run.py:_redirect():2444] Redirects installed.
+2025-11-16 13:22:54,740 INFO    MainThread:1342 [wandb_init.py:init():1080] run started, returning control to user process
+2025-11-16 13:23:26,077 INFO    MainThread:1342 [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', '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/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', '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', '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}
+2025-11-16 13:23:26,083 INFO    MainThread:1342 [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 0x7d02590afc20>>
+2025-11-16 13:23:26,083 INFO    MainThread:1342 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 177266693 None
+2025-11-16 13:30:54,626 INFO    MainThread:1342 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/ytv0as6f
+2025-11-16 13:30:54,628 INFO    MainThread:1342 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
+2025-11-16 13:30:54,628 INFO    MainThread:1342 [wandb_run.py:_restore():2451] restore
+2025-11-16 13:30:54,628 INFO    MainThread:1342 [wandb_run.py:_restore():2457] restore done
+2025-11-16 13:30:55,240 INFO    MainThread:1342 [wandb_run.py:_footer_sync_info():3853] logging synced files

wandb_logs/run-20251116_132253-ytv0as6f/run-ytv0as6f.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac427a1b1e772906a3efbbd573292d39f7e510b8dc6c0ba13be90a3b425a712
+size 175900

wandb_logs/run-20251116_133532-vuimo2u7/files/config.yaml

@@ -0,0 +1,542 @@
+_name_or_path:
+    value: ai4bharat/indic-bert
+_wandb:
+    value:
+        cli_version: 0.23.0
+        e:
+            eb4fr83dcibasi0tl0tmwy5o4v47w30l:
+                args:
+                    - configs/indic_bert.json
+                codePath: train.py
+                codePathLocal: train.py
+                cpu_count: 1
+                cpu_count_logical: 2
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "120942624768"
+                        used: "49643986944"
+                email: vijaysinghkushwaha3737@gmail.com
+                executable: /usr/bin/python3
+                git:
+                    commit: 49a00e4673c8e2994ddcb718dde864a99cc0961f
+                    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-6248e46d-a025-808c-15ca-20242f9a252c
+                host: 140cf68b228a
+                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: "2025-11-16T13:35:32.024509Z"
+                writerId: eb4fr83dcibasi0tl0tmwy5o4v47w30l
+        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: null
+attention_probs_dropout_prob:
+    value: 0
+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: 2
+chunk_size_feed_forward:
+    value: 0
+classifier_dropout_prob:
+    value: 0.1
+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
+disable_tqdm:
+    value: false
+diversity_penalty:
+    value: 0
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_sample:
+    value: false
+do_train:
+    value: false
+down_scale_factor:
+    value: 1
+dtype:
+    value: float32
+early_stopping:
+    value: false
+embedding_size:
+    value: 128
+encoder_no_repeat_ngram_size:
+    value: 0
+eos_token_id:
+    value: 3
+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
+gap_size:
+    value: 0
+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
+hidden_size:
+    value: 768
+hub_always_push:
+    value: false
+hub_model_id:
+    value: h3110Fr13nd/guj-eng-code-switch-indic-bert
+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
+inner_group_num:
+    value: 1
+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/indic-bert/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: ai4bharat/indic-bert
+model/num_parameters:
+    value: 32856837
+model_type:
+    value: albert
+mp_parameters:
+    value: ""
+neftune_noise_alpha:
+    value: null
+net_structure_type:
+    value: 0
+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_groups:
+    value: 1
+num_hidden_layers:
+    value: 12
+num_memory_blocks:
+    value: 0
+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/indic-bert
+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
+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-indic-bert
+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: data2/train.txt
+transformers_version:
+    value: 4.57.1
+type_vocab_size:
+    value: 2
+typical_p:
+    value: 1
+use_bfloat16:
+    value: false
+use_cpu:
+    value: false
+use_legacy_prediction_loop:
+    value: false
+use_liger_kernel:
+    value: false
+use_mps_device:
+    value: false
+vocab_size:
+    value: 200000
+warmup_ratio:
+    value: 0.1
+warmup_steps:
+    value: 0
+weight_decay:
+    value: 0.01

wandb_logs/run-20251116_133532-vuimo2u7/files/output.log

@@ -0,0 +1,83 @@
+
+    _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|
+    _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|
+    _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|
+    _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|
+    _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|
+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.
+config.json: 100% 507/507 [00:00<00:00, 1.86MB/s]
+spiece.model: 100% 5.65M/5.65M [00:00<00:00, 25.5MB/s]
+pytorch_model.bin: 100% 135M/135M [00:01<00:00, 85.1MB/s] 
+Some weights of AlbertForTokenClassification were not initialized from the model checkpoint at ai4bharat/indic-bert 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.
+100% 492/492 [01:34<00:00,  5.20it/s]
+{'loss': 1.5808, 'grad_norm': 8.045380592346191, 'learning_rate': 0.0, 'epoch': 0.01}
+{'loss': 1.3, 'grad_norm': 3.5511159896850586, 'learning_rate': 1.9600000000000002e-05, 'epoch': 0.3}
+{'loss': 0.6728, 'grad_norm': 5.11202335357666, 'learning_rate': 1.7782805429864253e-05, 'epoch': 0.61}
+{'loss': 0.417, 'grad_norm': 1.9782381057739258, 'learning_rate': 1.552036199095023e-05, 'epoch': 0.91}
+Processing Files (5 / 5)      : 100% 152M/152M [00:04<00:00, 36.2MB/s, 38.1MB/s  ] 
+{'eval_loss': 0.2685639560222626, 'eval_precision': 0.7524509803921569, 'eval_recall': 0.7181286549707603, 'eval_f1': 0.7348892878515858, 'eval_accuracy': 0.9420940970922251, 'eval_runtime': 2.0083, 'eval_samples_per_second': 162.324, 'eval_steps_per_second': 5.477, 'epoch': 1.0}
+{'loss': 0.2787, 'grad_norm': 18.289146423339844, 'learning_rate': 1.32579185520362e-05, 'epoch': 1.22}
+{'loss': 0.2075, 'grad_norm': 5.472610950469971, 'learning_rate': 1.0995475113122173e-05, 'epoch': 1.52}
+{'loss': 0.1602, 'grad_norm': 3.2986786365509033, 'learning_rate': 8.733031674208145e-06, 'epoch': 1.83}
+{'eval_loss': 0.1436997503042221, 'eval_precision': 0.8707403055229143, 'eval_recall': 0.8666666666666667, 'eval_f1': 0.8686987104337633, 'eval_accuracy': 0.9660551603644079, 'eval_runtime': 2.0933, 'eval_samples_per_second': 155.738, 'eval_steps_per_second': 5.255, 'epoch': 2.0}
+{'loss': 0.1614, 'grad_norm': 2.817918539047241, 'learning_rate': 6.470588235294119e-06, 'epoch': 2.13}
+{'loss': 0.1301, 'grad_norm': 3.798708915710449, 'learning_rate': 4.208144796380091e-06, 'epoch': 2.44}
+{'loss': 0.132, 'grad_norm': 4.0428009033203125, 'learning_rate': 1.9457013574660634e-06, 'epoch': 2.74}
+{'eval_loss': 0.0999612882733345, 'eval_precision': 0.8868360277136259, 'eval_recall': 0.8982456140350877, 'eval_f1': 0.8925043579314353, 'eval_accuracy': 0.9772869087732435, 'eval_runtime': 2.0984, 'eval_samples_per_second': 155.357, 'eval_steps_per_second': 5.242, 'epoch': 3.0}
+{'train_runtime': 94.6239, 'train_samples_per_second': 82.717, 'train_steps_per_second': 5.2, 'train_loss': 0.3611367323049685, 'epoch': 3.0}
+New Data Upload               : 100% 131M/131M [00:04<00:00, 31.2MB/s, 32.9MB/s  ] 
+  ...indic-bert/tokenizer.json: 100% 15.3M/15.3M [00:03<?, ?B/s]
+  ...s/indic-bert/spiece.model: 100% 5.65M/5.65M [00:03<?, ?B/s]
+  ...ic-bert/model.safetensors: 100% 131M/131M [00:03<00:00, 40.8MB/s] 
+  ...00157.140cf68b228a.4984.0: 100% 9.23k/9.23k [00:02<00:00, 3.51kB/s]
+  ...ic-bert/training_args.bin: 100% 5.91k/5.91k [00:02<00:00, 2.24kB/s]
+Processing Files (5 / 5)      : 100% 152M/152M [00:01<00:00, 126MB/s,  115MB/s  ] 
+New Data Upload               : |          |  0.00B /  0.00B,  0.00B/s  
+  ...ic-bert/training_args.bin: 100% 5.91k/5.91k [00:01<?, ?B/s]
+  ...00157.140cf68b228a.4984.0: 100% 9.23k/9.23k [00:01<?, ?B/s]
+  ...s/indic-bert/spiece.model: 100% 5.65M/5.65M [00:01<?, ?B/s]
+  ...indic-bert/tokenizer.json: 100% 15.3M/15.3M [00:01<?, ?B/s]
+  ...ic-bert/model.safetensors: 100% 131M/131M [00:01<00:00, 114MB/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               =    20092GF
+  train_loss               =     0.3611
+  train_runtime            = 0:01:34.62
+  train_samples_per_second =     82.717
+  train_steps_per_second   =        5.2
+100% 11/11 [00:02<00:00,  5.34it/s]
+***** eval metrics *****
+  epoch                   =        3.0
+  eval_accuracy           =     0.9773
+  eval_f1                 =     0.8925
+  eval_loss               =        0.1
+  eval_precision          =     0.8868
+  eval_recall             =     0.8982
+  eval_runtime            = 0:00:02.17
+  eval_samples_per_second =    149.596
+  eval_steps_per_second   =      5.048
+ 91% 10/11 [00:00<00:00,  9.24it/s]early stopping required metric_for_best_model, but did not find eval_f1 so early stopping is disabled
+100% 11/11 [00:01<00:00,  6.58it/s]
+***** test metrics *****
+  epoch                   =        3.0
+  test_accuracy           =     0.9755
+  test_f1                 =      0.893
+  test_loss               =     0.1121
+  test_precision          =     0.8925
+  test_recall             =     0.8935
+  test_runtime            = 0:00:01.80
+  test_samples_per_second =    180.672
+  test_steps_per_second   =      6.078

wandb_logs/run-20251116_133532-vuimo2u7/files/requirements.txt

@@ -0,0 +1,700 @@
+types-setuptools==80.9.0.20250822
+setuptools==75.2.0
+pip==24.1.2
+requirements-parser==0.9.0
+pandas==2.3.3
+tensorboard==2.20.0
+ipykernel==7.1.0
+seqeval==1.2.2
+google-genai==1.50.1
+widgetsnbextension==4.0.15
+evaluate==0.4.6
+jedi==0.19.2
+pyarrow==22.0.0
+datasets==4.4.1
+numpy==2.3.4
+scikit-learn==1.7.2
+wandb==0.23.0
+jupyter_client==8.6.3
+comm==0.2.3
+ipywidgets==8.1.8
+google-colab==1.0.0
+yfinance==0.2.66
+pytensor==2.35.1
+dask==2025.9.1
+ipython-sql==0.5.0
+libucxx-cu12==0.46.0
+duckdb==1.3.2
+h5py==3.15.1
+requests==2.32.4
+db-dtypes==1.4.4
+xyzservices==2025.10.0
+bigframes==2.28.0
+grpclib==0.4.8
+httpcore==1.0.9
+cudf-polars-cu12==25.10.0
+webcolors==25.10.0
+cvxopt==1.3.2
+google-cloud-bigquery-storage==2.34.0
+future==1.0.0
+nvidia-cuda-cccl-cu12==12.9.27
+tf_keras==2.19.0
+hf_transfer==0.1.9
+simple-parsing==0.1.7
+arviz==0.22.0
+opentelemetry-semantic-conventions==0.58b0
+click==8.3.0
+locket==1.0.0
+libpysal==4.13.0
+rsa==4.9.1
+distro==1.9.0
+nx-cugraph-cu12==25.10.0
+smmap==5.0.2
+google-auth-oauthlib==1.2.3
+tzlocal==5.3.1
+ipyfilechooser==0.6.0
+googledrivedownloader==1.1.0
+nvidia-cusparse-cu12==12.5.4.2
+jax-cuda12-plugin==0.7.2
+httpx-sse==0.4.3
+google-crc32c==1.7.1
+matplotlib==3.10.0
+pyomo==6.9.5
+jsonpatch==1.33
+jupyter-console==6.6.3
+Flask==3.1.2
+nibabel==5.3.2
+anyio==4.11.0
+matplotlib-venn==1.1.2
+pydantic_core==2.33.2
+fasttransform==0.0.2
+sortedcontainers==2.4.0
+astropy-iers-data==0.2025.11.10.0.38.31
+semantic-version==2.10.0
+preshed==3.0.10
+nbconvert==7.16.6
+pluggy==1.6.0
+wcwidth==0.2.14
+overrides==7.7.0
+sklearn-pandas==2.2.0
+google-cloud-functions==1.21.0
+sphinxcontrib-jsmath==1.0.1
+html5lib==1.1
+linkify-it-py==2.0.3
+ruff==0.14.4
+google-api-core==2.28.1
+pooch==1.8.2
+google-auth==2.38.0
+jsonpointer==3.0.0
+google-cloud-speech==2.34.0
+argon2-cffi==25.1.0
+orjson==3.11.4
+wheel==0.45.1
+typing_extensions==4.15.0
+uritemplate==4.2.0
+portpicker==1.5.2
+zipp==3.23.0
+cuda-python==12.9.4
+numexpr==2.14.1
+networkx==3.5
+progressbar2==4.5.0
+dm-tree==0.1.9
+ibis-framework==9.5.0
+jaraco.context==6.0.1
+threadpoolctl==3.6.0
+libkvikio-cu12==25.10.0
+betterproto==2.0.0b6
+pydantic-settings==2.12.0
+grpcio==1.76.0
+pyOpenSSL==24.2.1
+logical-unification==0.4.7
+nvidia-cusparselt-cu12==0.7.1
+folium==0.20.0
+stanio==0.5.1
+grpc-google-iam-v1==0.14.3
+ply==3.11
+confection==0.1.5
+httpx==0.28.1
+ffmpy==1.0.0
+gradio_client==1.13.3
+pandas-stubs==2.2.2.240909
+inflect==7.5.0
+osqp==1.0.5
+filelock==3.20.0
+lazy_loader==0.4
+toml==0.10.2
+audioread==3.1.0
+stringzilla==4.2.3
+nvidia-nvtx-cu12==12.6.77
+wordcloud==1.9.4
+rfc3986-validator==0.1.1
+blinker==1.9.0
+iniconfig==2.3.0
+sphinxcontrib-qthelp==2.0.0
+holidays==0.84
+tensorboard-data-server==0.7.2
+smart_open==7.5.0
+decorator==4.4.2
+plotnine==0.14.5
+omegaconf==2.3.0
+numba-cuda==0.19.1
+ipytree==0.2.2
+moviepy==1.0.3
+traitlets==5.7.1
+cuml-cu12==25.10.0
+debugpy==1.8.15
+PyJWT==2.10.1
+fonttools==4.60.1
+tensorflow-datasets==4.9.9
+absl-py==1.4.0
+etils==1.13.0
+ml_dtypes==0.5.3
+idna==3.11
+google-cloud-appengine-logging==1.7.0
+bokeh==3.7.3
+text-unidecode==1.3
+blis==1.3.0
+llvmlite==0.43.0
+multitasking==0.0.12
+msgpack==1.1.2
+tensorflow-text==2.19.0
+rfc3339-validator==0.1.4
+keras-hub==0.21.1
+jupyterlab_pygments==0.3.0
+yarl==1.22.0
+ipyevents==2.0.4
+xgboost==3.1.1
+zict==3.0.0
+torchtune==0.6.1
+spanner-graph-notebook==1.1.8
+patsy==1.0.2
+mizani==0.13.5
+fastcore==1.8.16
+et_xmlfile==2.0.0
+jeepney==0.9.0
+geopandas==1.1.1
+tinycss2==1.4.0
+backcall==0.2.0
+jiter==0.12.0
+flax==0.10.7
+PySocks==1.7.1
+Pygments==2.19.2
+hpack==4.1.0
+pytz==2025.2
+narwhals==2.11.0
+murmurhash==1.0.13
+slicer==0.0.8
+google-cloud-bigtable==2.34.0
+cmake==3.31.6
+antlr4-python3-runtime==4.9.3
+Jinja2==3.1.6
+python-slugify==8.0.4
+multiprocess==0.70.16
+gitdb==4.0.12
+proglog==0.1.12
+psygnal==0.15.0
+geographiclib==2.1
+jupyter_server==2.14.0
+requests-oauthlib==2.0.0
+plotly==5.24.1
+raft-dask-cu12==25.10.0
+torchao==0.10.0
+opencv-contrib-python==4.12.0.88
+dlib==19.24.6
+cuda-toolkit==12.9.1
+thinc==8.3.8
+Bottleneck==1.4.2
+regex==2024.11.6
+google-cloud-language==2.18.0
+cymem==2.0.11
+Authlib==1.6.5
+pyperclip==1.11.0
+ratelim==0.1.6
+mpmath==1.3.0
+astunparse==1.6.3
+missingno==0.5.2
+cmdstanpy==1.3.0
+tensorstore==0.1.78
+typeguard==4.4.4
+keras==3.10.0
+toolz==0.12.1
+nltk==3.9.1
+aiofiles==24.1.0
+albucore==0.0.24
+pycryptodomex==3.23.0
+pydantic==2.11.10
+websocket-client==1.9.0
+frozenlist==1.8.0
+glob2==0.7
+libraft-cu12==25.10.0
+tornado==6.5.1
+tweepy==4.16.0
+babel==2.17.0
+treelite==4.4.1
+librmm-cu12==25.10.0
+soxr==1.0.0
+xlrd==2.0.2
+tabulate==0.9.0
+PyYAML==6.0.3
+imageio-ffmpeg==0.6.0
+pyzmq==26.2.1
+webencodings==0.5.1
+tzdata==2025.2
+pickleshare==0.7.5
+opentelemetry-api==1.37.0
+chardet==5.2.0
+ptyprocess==0.7.0
+optree==0.17.0
+flatbuffers==25.9.23
+jsonpickle==4.1.1
+cramjam==2.11.0
+tables==3.10.2
+tf-slim==1.1.0
+fastai==2.8.5
+cloudpickle==3.1.2
+orbax-checkpoint==0.11.28
+soundfile==0.13.1
+highspy==1.12.0
+pexpect==4.9.0
+nbformat==5.10.4
+atpublic==5.1
+python-box==7.3.2
+miniKanren==1.0.5
+nbclient==0.10.2
+nvidia-cuda-runtime-cu12==12.6.77
+arrow==1.4.0
+dopamine_rl==4.1.2
+cuda-pathfinder==1.3.2
+google-cloud-core==2.5.0
+gspread==6.2.1
+PyOpenGL==3.1.10
+google==2.0.3
+fastjsonschema==2.21.2
+google-cloud-resource-manager==1.15.0
+mistune==3.1.4
+absolufy-imports==0.3.1
+annotated-doc==0.0.4
+scs==3.2.9
+kagglehub==0.3.13
+dask-cuda==25.10.0
+dill==0.3.8
+spacy==3.8.8
+tensorflow-metadata==1.17.2
+oauth2client==4.1.3
+rich==13.9.4
+python-dateutil==2.9.0.post0
+aiohttp==3.13.2
+tensorflow==2.19.0
+ipyparallel==8.8.0
+scikit-image==0.25.2
+anywidget==0.9.19
+etuples==0.3.10
+bqplot==0.12.45
+lightgbm==4.6.0
+opentelemetry-exporter-otlp-proto-http==1.37.0
+argon2-cffi-bindings==25.1.0
+libcuml-cu12==25.10.0
+tensorflow-hub==0.16.1
+branca==0.8.2
+google-auth-httplib2==0.2.1
+cryptography==43.0.3
+python-dotenv==1.2.1
+ImageIO==2.37.2
+aiohappyeyeballs==2.6.1
+ale-py==0.11.2
+httplib2==0.31.0
+jupyter-leaflet==0.20.0
+jupyter_core==5.9.1
+gspread-dataframe==4.0.0
+music21==9.3.0
+spacy-legacy==3.0.12
+gym==0.25.2
+traittypes==0.2.3
+nvidia-nccl-cu12==2.27.3
+altair==5.5.0
+tblib==3.2.1
+langchain==0.3.27
+pyspark==3.5.1
+optax==0.2.6
+build==1.3.0
+hyperopt==0.2.7
+google-cloud-trace==1.17.0
+sphinxcontrib-htmlhelp==2.1.0
+google-cloud-spanner==3.59.0
+cycler==0.12.1
+namex==0.1.0
+pymc==5.26.1
+Cython==3.0.12
+tensorflow-probability==0.25.0
+nvidia-cublas-cu12==12.6.4.1
+pylibcugraph-cu12==25.10.1
+beartype==0.22.5
+srsly==2.5.1
+lark==1.3.1
+h11==0.16.0
+grpc-interceptor==0.15.4
+psutil==5.9.5
+peewee==3.18.3
+nvidia-cuda-nvcc-cu12==12.9.86
+prompt_toolkit==3.0.52
+distributed-ucxx-cu12==0.46.0
+gymnasium==1.2.2
+gym-notices==0.1.0
+pandas-gbq==0.30.0
+ipython==7.34.0
+pycocotools==2.0.10
+uri-template==1.3.0
+earthengine-api==1.5.24
+jieba==0.42.1
+cloudpathlib==0.23.0
+markdown-it-py==4.0.0
+prettytable==3.16.0
+fastprogress==1.0.3
+parso==0.8.5
+prometheus_client==0.23.1
+google-pasta==0.2.0
+py-cpuinfo==9.0.0
+Mako==1.3.10
+distributed==2025.9.1
+grpcio-status==1.71.2
+wasabi==1.1.3
+google-cloud-secret-manager==2.25.0
+urllib3==2.5.0
+packaging==25.0
+python-louvain==0.16
+simplejson==3.20.2
+param==2.2.1
+sphinxcontrib-serializinghtml==2.0.0
+pyparsing==3.2.5
+Markdown==3.10
+alembic==1.17.1
+GDAL==3.8.4
+timm==1.0.22
+google-cloud-bigquery==3.38.0
+openpyxl==3.1.5
+tenacity==8.5.0
+bigquery-magics==0.10.3
+blobfile==3.1.0
+pygit2==1.19.0
+imbalanced-learn==0.14.0
+opentelemetry-exporter-gcp-monitoring==1.11.0a0
+termcolor==3.2.0
+pydot==3.0.4
+sse-starlette==3.0.3
+spacy-loggers==1.0.5
+rpds-py==0.28.0
+watchdog==6.0.0
+sentencepiece==0.2.1
+stumpy==1.13.0
+statsmodels==0.14.5
+google-adk==1.17.0
+isoduration==20.11.0
+community==1.0.0b1
+pillow==11.3.0
+alabaster==1.0.0
+contourpy==1.3.3
+google-cloud-datastore==2.21.0
+jax==0.7.2
+bleach==6.3.0
+panel==1.8.3
+attrs==25.4.0
+CacheControl==0.14.3
+mlxtend==0.23.4
+intel-openmp==2025.3.1
+umf==1.0.2
+google-cloud-translate==3.23.0
+google-cloud-storage==2.19.0
+nvidia-nvjitlink-cu12==12.6.85
+jsonschema==4.25.1
+python-snappy==0.7.3
+typer==0.20.0
+roman-numerals-py==3.1.0
+opentelemetry-exporter-gcp-trace==1.11.0
+pyproj==3.7.2
+opencv-python-headless==4.12.0.88
+google-resumable-media==2.7.2
+opentelemetry-proto==1.37.0
+chex==0.1.90
+geocoder==1.38.1
+fastapi==0.121.1
+beautifulsoup4==4.13.5
+textblob==0.19.0
+accelerate==1.11.0
+defusedxml==0.7.1
+jaraco.classes==3.4.0
+uc-micro-py==1.0.3
+curl_cffi==0.13.0
+hdbscan==0.8.40
+pydotplus==2.0.2
+pynndescent==0.5.13
+colour==0.1.5
+google-cloud-monitoring==2.28.0
+tensorflow_decision_forests==1.12.0
+einops==0.8.1
+rmm-cu12==25.10.0
+snowballstemmer==3.0.1
+jupyter_kernel_gateway==2.5.2
+groovy==0.1.2
+blosc2==3.11.0
+h5netcdf==1.7.3
+nvidia-cuda-nvrtc-cu12==12.6.77
+pyerfa==2.0.1.5
+psycopg2==2.9.11
+docutils==0.21.2
+google-ai-generativelanguage==0.6.15
+prophet==1.1.7
+pyviz_comms==3.0.6
+albumentations==2.0.8
+easydict==1.13
+Send2Trash==1.8.3
+rapids-logger==0.1.19
+mdurl==0.1.2
+frozendict==2.4.6
+nvidia-cufft-cu12==11.3.0.4
+sqlparse==0.5.3
+torchaudio==2.8.0+cu126
+simsimd==6.5.3
+nvidia-ml-py==13.580.82
+sentry-sdk==2.44.0
+nbclassic==1.3.3
+ydf==0.13.0
+nvidia-cusolver-cu12==11.7.1.2
+langchain-text-splitters==0.3.11
+numba==0.60.0
+PyGObject==3.42.0
+holoviews==1.22.0
+jupyterlab_widgets==3.0.16
+pycparser==2.23
+mkl==2025.2.0
+jupyter_server_terminals==0.5.3
+brotli==1.2.0
+promise==2.3
+ipyleaflet==0.20.0
+weasel==0.4.2
+httpimport==1.4.1
+nvidia-cudnn-cu12==9.10.2.21
+SQLAlchemy==2.0.44
+cons==0.4.7
+wrapt==2.0.1
+openai==1.109.1
+charset-normalizer==3.4.4
+peft==0.17.1
+gin-config==0.5.0
+shellingham==1.5.4
+soupsieve==2.8
+yellowbrick==1.5
+en_core_web_sm==3.8.0
+fsspec==2025.3.0
+google-cloud-firestore==2.21.0
+google-cloud-audit-log==0.4.0
+nvidia-cufile-cu12==1.11.1.6
+triton==3.4.0
+mdit-py-plugins==0.5.0
+platformdirs==4.5.0
+nest-asyncio==1.6.0
+hyperframe==6.1.0
+libucx-cu12==1.19.0
+docstring_parser==0.17.0
+nvtx==0.2.13
+cufflinks==0.17.3
+rpy2==3.5.17
+torchsummary==1.5.1
+eerepr==0.1.2
+array_record==0.8.2
+cvxpy==1.6.7
+opentelemetry-exporter-gcp-logging==1.11.0a0
+typing-inspection==0.4.2
+ucxx-cu12==0.46.0
+gradio==5.49.1
+types-pytz==2025.2.0.20251108
+safehttpx==0.1.7
+safetensors==0.6.2
+opentelemetry-resourcedetector-gcp==1.11.0a0
+aiosignal==1.4.0
+librosa==0.11.0
+websockets==15.0.1
+opt_einsum==3.4.0
+clarabel==0.11.1
+pyshp==3.0.2.post1
+sqlglot==25.20.2
+fastrlock==0.8.3
+kiwisolver==1.4.9
+google-api-python-client==2.187.0
+uvicorn==0.38.0
+scooby==0.11.0
+shap==0.50.0
+keyring==25.6.0
+opencv-python==4.12.0.88
+typer-slim==0.20.0
+terminado==0.18.1
+protobuf==5.29.5
+google-cloud-dataproc==5.23.0
+pytest==8.4.2
+pandas-datareader==0.10.0
+pylibcudf-cu12==25.10.0
+opentelemetry-exporter-otlp-proto-common==1.37.0
+mcp==1.21.0
+diffusers==0.35.2
+tiktoken==0.12.0
+opentelemetry-sdk==1.37.0
+SecretStorage==3.4.1
+colorlover==0.3.0
+nvidia-curand-cu12==10.3.7.77
+libcudf-cu12==25.10.0
+geopy==2.4.1
+torchdata==0.11.0
+geemap==0.35.3
+Sphinx==8.2.3
+proto-plus==1.26.1
+graphviz==0.21
+wurlitzer==3.1.1
+kaggle==1.7.4.5
+firebase-admin==6.9.0
+shapely==2.1.2
+astropy==7.1.1
+zstandard==0.25.0
+torch==2.8.0+cu126
+polars==1.31.0
+tokenizers==0.22.1
+ipython-genutils==0.2.0
+python-utils==3.9.1
+python-multipart==0.0.20
+vega-datasets==0.9.0
+treescope==0.1.10
+sniffio==1.3.1
+fqdn==1.5.1
+google-cloud-bigquery-connection==1.19.0
+jax-cuda12-pjrt==0.7.2
+editdistance==0.8.1
+multidict==6.7.0
+PyWavelets==1.9.0
+pydata-google-auth==1.9.1
+importlib_resources==6.5.2
+intel-cmplr-lib-ur==2025.3.1
+sphinxcontrib-applehelp==2.0.0
+fastdownload==0.0.7
+autograd==1.8.0
+tqdm==4.67.1
+notebook==6.5.7
+greenlet==3.2.4
+xxhash==3.6.0
+immutabledict==4.2.2
+sentence-transformers==5.1.2
+imutils==0.5.4
+umap-learn==0.5.9.post2
+tbb==2022.3.0
+python-json-logger==4.0.0
+matplotlib-inline==0.2.1
+joblib==1.5.2
+pycairo==1.29.0
+gcsfs==2025.3.0
+huggingface-hub==0.36.0
+google-generativeai==0.8.5
+imagesize==1.4.1
+langchain-core==0.3.79
+hf-xet==1.2.0
+pygame==2.6.1
+gdown==5.2.0
+dataproc-spark-connect==0.8.3
+transformers==4.57.1
+multipledispatch==1.0.0
+jaraco.functools==4.3.0
+colorcet==3.1.0
+tomlkit==0.13.3
+notebook_shim==0.2.4
+keyrings.google-artifactregistry-auth==1.1.2
+xarray==2025.10.1
+six==1.17.0
+jaxlib==0.7.2
+google-cloud-aiplatform==1.126.1
+certifi==2025.10.5
+catalogue==2.0.10
+humanize==4.14.0
+parsy==2.2
+cuda-bindings==12.9.4
+rfc3987-syntax==1.1.0
+propcache==0.4.1
+cachetools==5.5.2
+google-cloud-logging==3.12.1
+cffi==2.0.0
+googleapis-common-protos==1.72.0
+tcmlib==1.4.1
+cuda-core==0.3.2
+py4j==0.10.9.7
+pyogrio==0.11.1
+requests-toolbelt==1.0.0
+seaborn==0.13.2
+sphinxcontrib-devhelp==2.0.0
+referencing==0.37.0
+pylibraft-cu12==25.10.0
+more-itertools==10.8.0
+entrypoints==0.4
+keras-nlp==0.21.1
+libcugraph-cu12==25.10.1
+sympy==1.13.3
+PyDrive2==1.21.3
+natsort==8.4.0
+cupy-cuda12x==13.6.0
+h2==4.3.0
+jupyter-events==0.12.0
+google-cloud-discoveryengine==0.13.12
+itsdangerous==2.2.0
+pydub==0.25.1
+nvidia-nvshmem-cu12==3.4.5
+sqlalchemy-spanner==1.17.1
+gast==0.6.0
+partd==1.4.2
+pyasn1_modules==0.4.2
+dask-cudf-cu12==25.10.0
+cudf-cu12==25.10.0
+plum-dispatch==2.6.0
+pyasn1==0.6.1
+pandocfilters==1.5.1
+libclang==18.1.1
+xarray-einstats==0.9.1
+nvidia-cuda-cupti-cu12==12.6.80
+torchvision==0.23.0+cu126
+GitPython==3.1.45
+oauthlib==3.3.1
+cyipopt==1.5.0
+MarkupSafe==3.0.3
+langsmith==0.4.42
+starlette==0.49.3
+Farama-Notifications==0.0.4
+lxml==5.4.0
+jsonschema-specifications==2025.9.1
+jupytext==1.17.3
+scipy==1.16.3
+tifffile==2025.10.16
+tsfresh==0.21.1
+importlib_metadata==8.7.0
+annotated-types==0.7.0
+pyproject_hooks==1.2.0
+Werkzeug==3.1.3
+ndindex==1.10.0
+rapids-dask-dependency==25.10.0
+python-apt==0.0.0
+pyparsing==2.4.7
+SecretStorage==3.3.1
+more-itertools==8.10.0
+cryptography==3.4.8
+six==1.16.0
+blinker==1.4
+httplib2==0.20.2
+keyring==23.5.0
+lazr.restfulclient==0.14.4
+PyGObject==3.42.1
+PyJWT==2.3.0
+importlib-metadata==4.6.4
+wadllib==1.3.6
+dbus-python==1.2.18
+oauthlib==3.2.0
+lazr.uri==1.0.6
+jeepney==0.7.1
+zipp==1.0.0
+distro==1.7.0
+launchpadlib==1.10.16
+python-apt==2.4.0+ubuntu4
+Mako==1.1.3
+Markdown==3.3.6
+MarkupSafe==2.0.1

wandb_logs/run-20251116_133532-vuimo2u7/files/wandb-metadata.json

@@ -0,0 +1,43 @@
+{
+  "os": "Linux-6.6.105+-x86_64-with-glibc2.35",
+  "python": "CPython 3.12.12",
+  "startedAt": "2025-11-16T13:35:32.024509Z",
+  "args": [
+    "configs/indic_bert.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": "49a00e4673c8e2994ddcb718dde864a99cc0961f"
+  },
+  "email": "vijaysinghkushwaha3737@gmail.com",
+  "root": "/content/code-switch-identification-model",
+  "host": "140cf68b228a",
+  "executable": "/usr/bin/python3",
+  "cpu_count": 1,
+  "cpu_count_logical": 2,
+  "gpu": "Tesla T4",
+  "gpu_count": 1,
+  "disk": {
+    "/": {
+      "total": "120942624768",
+      "used": "49643986944"
+    }
+  },
+  "memory": {
+    "total": "13605851136"
+  },
+  "gpu_nvidia": [
+    {
+      "name": "Tesla T4",
+      "memoryTotal": "16106127360",
+      "cudaCores": 2560,
+      "architecture": "Turing",
+      "uuid": "GPU-6248e46d-a025-808c-15ca-20242f9a252c"
+    }
+  ],
+  "cudaVersion": "12.4",
+  "writerId": "eb4fr83dcibasi0tl0tmwy5o4v47w30l"
+}

wandb_logs/run-20251116_133532-vuimo2u7/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_timestamp":1.763300266947719e+09,"eval/loss":0.0999612882733345,"_step":15,"test/recall":0.8935447338618346,"test/runtime":1.8099,"train_steps_per_second":5.2,"eval/precision":0.8868360277136259,"eval/samples_per_second":149.596,"train_runtime":94.6239,"test/accuracy":0.9754616132167152,"_wandb":{"runtime":134},"test/samples_per_second":180.672,"test/precision":0.8925339366515838,"eval/f1":0.8925043579314353,"train_samples_per_second":82.717,"test/steps_per_second":6.078,"train/epoch":3,"_runtime":134,"eval/recall":0.8982456140350877,"train/loss":0.132,"test/loss":0.11211133748292923,"train/global_step":492,"train/grad_norm":4.0428009033203125,"eval/accuracy":0.9772869087732435,"test/f1":0.8930390492359932,"eval/runtime":2.1792,"eval/steps_per_second":5.048,"train/learning_rate":1.9457013574660634e-06,"train_loss":0.3611367323049685,"total_flos":2.157451568064e+13}

wandb_logs/run-20251116_133532-vuimo2u7/logs/debug-core.log

@@ -0,0 +1,8 @@
+{"time":"2025-11-16T13:35:32.157434031Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpa1380fj4/port-4984.txt","pid":4984,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2025-11-16T13:35:32.158754588Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-4984-5062-2761496823/socket","Net":"unix"}}
+{"time":"2025-11-16T13:35:32.15890978Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":4984}
+{"time":"2025-11-16T13:35:32.337263835Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2025-11-16T13:35:32.343565201Z","level":"INFO","msg":"handleInformInit: received","streamId":"vuimo2u7","id":"1(@)"}
+{"time":"2025-11-16T13:35:32.544820465Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"vuimo2u7","id":"1(@)"}
+{"time":"2025-11-16T13:37:47.584038587Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"vuimo2u7","id":"1(@)"}
+{"time":"2025-11-16T13:37:47.589441999Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"vuimo2u7","id":"1(@)"}

wandb_logs/run-20251116_133532-vuimo2u7/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2025-11-16T13:35:32.343727177Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
+{"time":"2025-11-16T13:35:32.543953023Z","level":"INFO","msg":"stream: created new stream","id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.544489786Z","level":"INFO","msg":"writer: started","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.54453477Z","level":"INFO","msg":"handler: started","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.544772028Z","level":"INFO","msg":"sender: started","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:35:32.544809026Z","level":"INFO","msg":"stream: started","id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.428356763Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-11-16T13:37:47.579481888Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-11-16T13:37:47.58406537Z","level":"INFO","msg":"stream: closing","id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.584085955Z","level":"INFO","msg":"handler: closed","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.584139239Z","level":"INFO","msg":"sender: closed","stream_id":"vuimo2u7"}
+{"time":"2025-11-16T13:37:47.584148422Z","level":"INFO","msg":"stream: closed","id":"vuimo2u7"}

wandb_logs/run-20251116_133532-vuimo2u7/logs/debug.log

@@ -0,0 +1,29 @@
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Configure stats pid to 4984
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251116_133532-vuimo2u7/logs/debug.log
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251116_133532-vuimo2u7/logs/debug-internal.log
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:init():840] calling init triggers
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
+config: {'model': 'ai4bharat/indic-bert', 'train_file': 'data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
+2025-11-16 13:35:32,026 INFO    MainThread:4984 [wandb_init.py:init():888] starting backend
+2025-11-16 13:35:32,337 INFO    MainThread:4984 [wandb_init.py:init():891] sending inform_init request
+2025-11-16 13:35:32,341 INFO    MainThread:4984 [wandb_init.py:init():899] backend started and connected
+2025-11-16 13:35:32,345 INFO    MainThread:4984 [wandb_init.py:init():969] updated telemetry
+2025-11-16 13:35:32,368 INFO    MainThread:4984 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
+2025-11-16 13:35:32,820 INFO    MainThread:4984 [wandb_init.py:init():1040] starting run threads in backend
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_console_start():2504] atexit reg
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_redirect():2352] redirect: wrap_raw
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_redirect():2421] Wrapping output streams.
+2025-11-16 13:35:33,335 INFO    MainThread:4984 [wandb_run.py:_redirect():2444] Redirects installed.
+2025-11-16 13:35:33,337 INFO    MainThread:4984 [wandb_init.py:init():1080] run started, returning control to user process
+2025-11-16 13:35:57,698 INFO    MainThread:4984 [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': None, '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': 2, 'pad_token_id': 0, 'eos_token_id': 3, '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': 'ai4bharat/indic-bert', 'transformers_version': '4.57.1', 'model_type': 'albert', 'net_structure_type': 0, 'gap_size': 0, 'num_memory_blocks': 0, 'down_scale_factor': 1, 'tf_legacy_loss': False, 'use_bfloat16': False, 'vocab_size': 200000, 'embedding_size': 128, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_hidden_groups': 1, 'num_attention_heads': 12, 'inner_group_num': 1, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0, 'attention_probs_dropout_prob': 0, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'classifier_dropout_prob': 0.1, 'position_embedding_type': 'absolute', 'output_attentions': False, 'output_dir': './models/indic-bert', '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/indic-bert/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-indic-bert', '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-indic-bert', '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}
+2025-11-16 13:35:57,704 INFO    MainThread:4984 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 32856837 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x151bdd652270>>
+2025-11-16 13:35:57,704 INFO    MainThread:4984 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 32856837 None
+2025-11-16 13:37:46,953 INFO    MainThread:4984 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/vuimo2u7
+2025-11-16 13:37:46,954 INFO    MainThread:4984 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
+2025-11-16 13:37:46,955 INFO    MainThread:4984 [wandb_run.py:_restore():2451] restore
+2025-11-16 13:37:46,955 INFO    MainThread:4984 [wandb_run.py:_restore():2457] restore done
+2025-11-16 13:37:47,583 INFO    MainThread:4984 [wandb_run.py:_footer_sync_info():3853] logging synced files

wandb_logs/run-20251116_133532-vuimo2u7/run-vuimo2u7.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edff7a09f14b4ad4e371f66f25f494990ea0d23b606ee782e057522871f60a7b
+size 134260