h3110Fr13nd commited on
Commit
4521db3
·
verified ·
1 Parent(s): 5abffbb

Upload W&B logs

Browse files
.gitattributes CHANGED
@@ -37,3 +37,5 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  wandb_logs/run-20251122_161333-76f9jnsn/run-76f9jnsn.wandb filter=lfs diff=lfs merge=lfs -text
38
  wandb_logs/run-20251122_162012-g5qyspo9/run-g5qyspo9.wandb filter=lfs diff=lfs merge=lfs -text
39
  wandb_logs/run-20251122_162942-hn6dt5mn/run-hn6dt5mn.wandb filter=lfs diff=lfs merge=lfs -text
 
 
 
37
  wandb_logs/run-20251122_161333-76f9jnsn/run-76f9jnsn.wandb filter=lfs diff=lfs merge=lfs -text
38
  wandb_logs/run-20251122_162012-g5qyspo9/run-g5qyspo9.wandb filter=lfs diff=lfs merge=lfs -text
39
  wandb_logs/run-20251122_162942-hn6dt5mn/run-hn6dt5mn.wandb filter=lfs diff=lfs merge=lfs -text
40
+ wandb_logs/run-20251122_173629-7f2wzkw5/run-7f2wzkw5.wandb filter=lfs diff=lfs merge=lfs -text
41
+ wandb_logs/run-20251122_174431-8mhq2ivv/run-8mhq2ivv.wandb filter=lfs diff=lfs merge=lfs -text
wandb_logs/debug-internal.log CHANGED
@@ -1,12 +1,12 @@
1
- {"time":"2025-11-22T16:29:43.112498425Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
2
- {"time":"2025-11-22T16:29:43.288903484Z","level":"INFO","msg":"stream: created new stream","id":"hn6dt5mn"}
3
- {"time":"2025-11-22T16:29:43.288968184Z","level":"INFO","msg":"handler: started","stream_id":"hn6dt5mn"}
4
- {"time":"2025-11-22T16:29:43.289175576Z","level":"INFO","msg":"stream: started","id":"hn6dt5mn"}
5
- {"time":"2025-11-22T16:29:43.289197484Z","level":"INFO","msg":"writer: started","stream_id":"hn6dt5mn"}
6
- {"time":"2025-11-22T16:29:43.289219512Z","level":"INFO","msg":"sender: started","stream_id":"hn6dt5mn"}
7
- {"time":"2025-11-22T16:32:11.640166623Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
8
- {"time":"2025-11-22T16:32:11.775962676Z","level":"INFO","msg":"handler: operation stats","stats":{}}
9
- {"time":"2025-11-22T16:32:11.781320506Z","level":"INFO","msg":"stream: closing","id":"hn6dt5mn"}
10
- {"time":"2025-11-22T16:32:11.781339251Z","level":"INFO","msg":"handler: closed","stream_id":"hn6dt5mn"}
11
- {"time":"2025-11-22T16:32:11.781409336Z","level":"INFO","msg":"sender: closed","stream_id":"hn6dt5mn"}
12
- {"time":"2025-11-22T16:32:11.781430044Z","level":"INFO","msg":"stream: closed","id":"hn6dt5mn"}
 
1
+ {"time":"2025-11-22T17:44:31.771534275Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
2
+ {"time":"2025-11-22T17:44:32.141333974Z","level":"INFO","msg":"stream: created new stream","id":"8mhq2ivv"}
3
+ {"time":"2025-11-22T17:44:32.141411383Z","level":"INFO","msg":"handler: started","stream_id":"8mhq2ivv"}
4
+ {"time":"2025-11-22T17:44:32.141580901Z","level":"INFO","msg":"stream: started","id":"8mhq2ivv"}
5
+ {"time":"2025-11-22T17:44:32.141611972Z","level":"INFO","msg":"writer: started","stream_id":"8mhq2ivv"}
6
+ {"time":"2025-11-22T17:44:32.141632683Z","level":"INFO","msg":"sender: started","stream_id":"8mhq2ivv"}
7
+ {"time":"2025-11-22T17:52:55.145401145Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
8
+ {"time":"2025-11-22T17:52:55.467651839Z","level":"INFO","msg":"handler: operation stats","stats":{}}
9
+ {"time":"2025-11-22T17:52:55.472375271Z","level":"INFO","msg":"stream: closing","id":"8mhq2ivv"}
10
+ {"time":"2025-11-22T17:52:55.472396045Z","level":"INFO","msg":"handler: closed","stream_id":"8mhq2ivv"}
11
+ {"time":"2025-11-22T17:52:55.472483691Z","level":"INFO","msg":"sender: closed","stream_id":"8mhq2ivv"}
12
+ {"time":"2025-11-22T17:52:55.472505222Z","level":"INFO","msg":"stream: closed","id":"8mhq2ivv"}
wandb_logs/debug.log CHANGED
@@ -1,29 +1,29 @@
1
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
2
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_setup.py:_flush():80] Configure stats pid to 6429
3
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
4
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
5
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_setup.py:_flush():80] Loading settings from environment variables
6
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_162942-hn6dt5mn/logs/debug.log
7
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_162942-hn6dt5mn/logs/debug-internal.log
8
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_init.py:init():840] calling init triggers
9
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
10
  config: {'model': 'ai4bharat/indic-bert', 'train_file': 'synthetic_data_gen/data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
11
- 2025-11-22 16:29:42,812 INFO MainThread:6429 [wandb_init.py:init():888] starting backend
12
- 2025-11-22 16:29:43,105 INFO MainThread:6429 [wandb_init.py:init():891] sending inform_init request
13
- 2025-11-22 16:29:43,110 INFO MainThread:6429 [wandb_init.py:init():899] backend started and connected
14
- 2025-11-22 16:29:43,115 INFO MainThread:6429 [wandb_init.py:init():969] updated telemetry
15
- 2025-11-22 16:29:43,122 INFO MainThread:6429 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
16
- 2025-11-22 16:29:43,538 INFO MainThread:6429 [wandb_init.py:init():1040] starting run threads in backend
17
- 2025-11-22 16:29:44,015 INFO MainThread:6429 [wandb_run.py:_console_start():2504] atexit reg
18
- 2025-11-22 16:29:44,015 INFO MainThread:6429 [wandb_run.py:_redirect():2352] redirect: wrap_raw
19
- 2025-11-22 16:29:44,015 INFO MainThread:6429 [wandb_run.py:_redirect():2421] Wrapping output streams.
20
- 2025-11-22 16:29:44,015 INFO MainThread:6429 [wandb_run.py:_redirect():2444] Redirects installed.
21
- 2025-11-22 16:29:44,018 INFO MainThread:6429 [wandb_init.py:init():1080] run started, returning control to user process
22
- 2025-11-22 16:30:23,582 INFO MainThread:6429 [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-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/indic-bert-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'h3110Fr13nd/guj-eng-code-switch-indic-bert-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-indic-bert-data2', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
23
- 2025-11-22 16:30:23,587 INFO MainThread:6429 [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 0x7a1dac4b07d0>>
24
- 2025-11-22 16:30:23,587 INFO MainThread:6429 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 32856837 None
25
- 2025-11-22 16:32:11,129 INFO MainThread:6429 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/hn6dt5mn
26
- 2025-11-22 16:32:11,130 INFO MainThread:6429 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
27
- 2025-11-22 16:32:11,130 INFO MainThread:6429 [wandb_run.py:_restore():2451] restore
28
- 2025-11-22 16:32:11,130 INFO MainThread:6429 [wandb_run.py:_restore():2457] restore done
29
- 2025-11-22 16:32:11,780 INFO MainThread:6429 [wandb_run.py:_footer_sync_info():3853] logging synced files
 
1
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
2
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Configure stats pid to 3693
3
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
4
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
5
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Loading settings from environment variables
6
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_174431-8mhq2ivv/logs/debug.log
7
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_174431-8mhq2ivv/logs/debug-internal.log
8
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:init():840] calling init triggers
9
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
10
  config: {'model': 'ai4bharat/indic-bert', 'train_file': 'synthetic_data_gen/data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
11
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:init():888] starting backend
12
+ 2025-11-22 17:44:31,763 INFO MainThread:3693 [wandb_init.py:init():891] sending inform_init request
13
+ 2025-11-22 17:44:31,767 INFO MainThread:3693 [wandb_init.py:init():899] backend started and connected
14
+ 2025-11-22 17:44:31,774 INFO MainThread:3693 [wandb_init.py:init():969] updated telemetry
15
+ 2025-11-22 17:44:31,793 INFO MainThread:3693 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
16
+ 2025-11-22 17:44:32,570 INFO MainThread:3693 [wandb_init.py:init():1040] starting run threads in backend
17
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_console_start():2504] atexit reg
18
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_redirect():2352] redirect: wrap_raw
19
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_redirect():2421] Wrapping output streams.
20
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_redirect():2444] Redirects installed.
21
+ 2025-11-22 17:44:33,043 INFO MainThread:3693 [wandb_init.py:init():1080] run started, returning control to user process
22
+ 2025-11-22 17:49:59,523 INFO MainThread:3693 [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-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/indic-bert-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'h3110Fr13nd/guj-eng-code-switch-indic-bert-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-indic-bert-data2', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
23
+ 2025-11-22 17:49:59,527 INFO MainThread:3693 [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 0x7f632c2004a0>>
24
+ 2025-11-22 17:49:59,528 INFO MainThread:3693 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 32856837 None
25
+ 2025-11-22 17:52:53,688 INFO MainThread:3693 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/8mhq2ivv
26
+ 2025-11-22 17:52:53,689 INFO MainThread:3693 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
27
+ 2025-11-22 17:52:53,690 INFO MainThread:3693 [wandb_run.py:_restore():2451] restore
28
+ 2025-11-22 17:52:53,690 INFO MainThread:3693 [wandb_run.py:_restore():2457] restore done
29
+ 2025-11-22 17:52:55,471 INFO MainThread:3693 [wandb_run.py:_footer_sync_info():3853] logging synced files
wandb_logs/run-20251122_173629-7f2wzkw5/files/config.yaml ADDED
@@ -0,0 +1,543 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _name_or_path:
2
+ value: bert-base-multilingual-cased
3
+ _wandb:
4
+ value:
5
+ cli_version: 0.23.0
6
+ e:
7
+ zyfw9xtja269bha0ppac3mxoy5904j9p:
8
+ args:
9
+ - configs/bert_data2.json
10
+ codePath: train.py
11
+ codePathLocal: train.py
12
+ cpu_count: 1
13
+ cpu_count_logical: 2
14
+ cudaVersion: "12.4"
15
+ disk:
16
+ /:
17
+ total: "120942624768"
18
+ used: "41433153536"
19
+ email: vijaysinghkushwaha3737@gmail.com
20
+ executable: /usr/bin/python3
21
+ git:
22
+ commit: c280afc6ba26ad46a6cf9a434272dbf927fafc80
23
+ remote: https://h3110Fr13nd:@github.com/h3110Fr13nd/code-switch-identification-model.git
24
+ gpu: Tesla T4
25
+ gpu_count: 1
26
+ gpu_nvidia:
27
+ - architecture: Turing
28
+ cudaCores: 2560
29
+ memoryTotal: "16106127360"
30
+ name: Tesla T4
31
+ uuid: GPU-1b701237-0e57-cd79-3d08-bb01f3fff16f
32
+ host: 8b09dd3d6919
33
+ memory:
34
+ total: "13605851136"
35
+ os: Linux-6.6.105+-x86_64-with-glibc2.35
36
+ program: /content/code-switch-identification-model/train.py
37
+ python: CPython 3.12.12
38
+ root: /content/code-switch-identification-model
39
+ startedAt: "2025-11-22T17:36:29.567968Z"
40
+ writerId: zyfw9xtja269bha0ppac3mxoy5904j9p
41
+ m:
42
+ - "1": train/global_step
43
+ "6":
44
+ - 3
45
+ "7": []
46
+ - "2": '*'
47
+ "5": 1
48
+ "6":
49
+ - 1
50
+ "7": []
51
+ python_version: 3.12.12
52
+ t:
53
+ "1":
54
+ - 1
55
+ - 2
56
+ - 3
57
+ - 5
58
+ - 11
59
+ - 12
60
+ - 41
61
+ - 49
62
+ - 51
63
+ - 53
64
+ - 71
65
+ - 98
66
+ - 100
67
+ - 105
68
+ "2":
69
+ - 1
70
+ - 2
71
+ - 3
72
+ - 5
73
+ - 11
74
+ - 12
75
+ - 41
76
+ - 49
77
+ - 51
78
+ - 53
79
+ - 71
80
+ - 98
81
+ - 100
82
+ - 105
83
+ "3":
84
+ - 2
85
+ - 7
86
+ - 13
87
+ - 15
88
+ - 16
89
+ - 19
90
+ - 62
91
+ - 66
92
+ "4": 3.12.12
93
+ "5": 0.23.0
94
+ "6": 4.57.1
95
+ "9":
96
+ "1": transformers_trainer
97
+ "12": 0.23.0
98
+ "13": linux-x86_64
99
+ accelerator_config:
100
+ value:
101
+ dispatch_batches: null
102
+ even_batches: true
103
+ gradient_accumulation_kwargs: null
104
+ non_blocking: false
105
+ split_batches: false
106
+ use_seedable_sampler: true
107
+ adafactor:
108
+ value: false
109
+ adam_beta1:
110
+ value: 0.9
111
+ adam_beta2:
112
+ value: 0.999
113
+ adam_epsilon:
114
+ value: 1e-08
115
+ add_cross_attention:
116
+ value: false
117
+ architectures:
118
+ value:
119
+ - BertForMaskedLM
120
+ attention_probs_dropout_prob:
121
+ value: 0.1
122
+ auto_find_batch_size:
123
+ value: false
124
+ average_tokens_across_devices:
125
+ value: true
126
+ bad_words_ids:
127
+ value: null
128
+ batch_eval_metrics:
129
+ value: false
130
+ batch_size:
131
+ value: 16
132
+ begin_suppress_tokens:
133
+ value: null
134
+ bf16:
135
+ value: false
136
+ bf16_full_eval:
137
+ value: false
138
+ bos_token_id:
139
+ value: null
140
+ chunk_size_feed_forward:
141
+ value: 0
142
+ classifier_dropout:
143
+ value: null
144
+ cross_attention_hidden_size:
145
+ value: null
146
+ data_seed:
147
+ value: null
148
+ dataloader_drop_last:
149
+ value: false
150
+ dataloader_num_workers:
151
+ value: 0
152
+ dataloader_persistent_workers:
153
+ value: false
154
+ dataloader_pin_memory:
155
+ value: true
156
+ dataloader_prefetch_factor:
157
+ value: null
158
+ ddp_backend:
159
+ value: null
160
+ ddp_broadcast_buffers:
161
+ value: null
162
+ ddp_bucket_cap_mb:
163
+ value: null
164
+ ddp_find_unused_parameters:
165
+ value: null
166
+ ddp_timeout:
167
+ value: 1800
168
+ debug:
169
+ value: []
170
+ decoder_start_token_id:
171
+ value: null
172
+ deepspeed:
173
+ value: null
174
+ directionality:
175
+ value: bidi
176
+ disable_tqdm:
177
+ value: false
178
+ diversity_penalty:
179
+ value: 0
180
+ do_eval:
181
+ value: true
182
+ do_predict:
183
+ value: false
184
+ do_sample:
185
+ value: false
186
+ do_train:
187
+ value: false
188
+ dtype:
189
+ value: float32
190
+ early_stopping:
191
+ value: false
192
+ encoder_no_repeat_ngram_size:
193
+ value: 0
194
+ eos_token_id:
195
+ value: null
196
+ epochs:
197
+ value: 3
198
+ eval_accumulation_steps:
199
+ value: null
200
+ eval_delay:
201
+ value: 0
202
+ eval_do_concat_batches:
203
+ value: true
204
+ eval_on_start:
205
+ value: false
206
+ eval_steps:
207
+ value: null
208
+ eval_strategy:
209
+ value: epoch
210
+ eval_use_gather_object:
211
+ value: false
212
+ exponential_decay_length_penalty:
213
+ value: null
214
+ finetuning_task:
215
+ value: null
216
+ forced_bos_token_id:
217
+ value: null
218
+ forced_eos_token_id:
219
+ value: null
220
+ fp16:
221
+ value: false
222
+ fp16_backend:
223
+ value: auto
224
+ fp16_full_eval:
225
+ value: false
226
+ fp16_opt_level:
227
+ value: O1
228
+ fsdp:
229
+ value: []
230
+ fsdp_config:
231
+ value:
232
+ min_num_params: 0
233
+ xla: false
234
+ xla_fsdp_grad_ckpt: false
235
+ xla_fsdp_v2: false
236
+ fsdp_min_num_params:
237
+ value: 0
238
+ fsdp_transformer_layer_cls_to_wrap:
239
+ value: null
240
+ full_determinism:
241
+ value: false
242
+ gradient_accumulation_steps:
243
+ value: 1
244
+ gradient_checkpointing:
245
+ value: false
246
+ gradient_checkpointing_kwargs:
247
+ value: null
248
+ greater_is_better:
249
+ value: true
250
+ group_by_length:
251
+ value: false
252
+ half_precision_backend:
253
+ value: auto
254
+ hidden_act:
255
+ value: gelu
256
+ hidden_dropout_prob:
257
+ value: 0.1
258
+ hidden_size:
259
+ value: 768
260
+ hub_always_push:
261
+ value: false
262
+ hub_model_id:
263
+ value: h3110Fr13nd/guj-eng-code-switch-bert-multilingual-data2
264
+ hub_private_repo:
265
+ value: false
266
+ hub_revision:
267
+ value: null
268
+ hub_strategy:
269
+ value: end
270
+ hub_token:
271
+ value: <HUB_TOKEN>
272
+ id2label:
273
+ value:
274
+ "0": O
275
+ "1": B-GUJ
276
+ "2": I-GUJ
277
+ "3": B-ENG
278
+ "4": I-ENG
279
+ ignore_data_skip:
280
+ value: false
281
+ include_for_metrics:
282
+ value: []
283
+ include_inputs_for_metrics:
284
+ value: false
285
+ include_num_input_tokens_seen:
286
+ value: "no"
287
+ include_tokens_per_second:
288
+ value: false
289
+ initializer_range:
290
+ value: 0.02
291
+ intermediate_size:
292
+ value: 3072
293
+ is_decoder:
294
+ value: false
295
+ is_encoder_decoder:
296
+ value: false
297
+ jit_mode_eval:
298
+ value: false
299
+ label_names:
300
+ value: null
301
+ label_smoothing_factor:
302
+ value: 0
303
+ label2id:
304
+ value:
305
+ B-ENG: 3
306
+ B-GUJ: 1
307
+ I-ENG: 4
308
+ I-GUJ: 2
309
+ O: 0
310
+ layer_norm_eps:
311
+ value: 1e-12
312
+ learning_rate:
313
+ value: 2e-05
314
+ length_column_name:
315
+ value: length
316
+ length_penalty:
317
+ value: 1
318
+ liger_kernel_config:
319
+ value: null
320
+ load_best_model_at_end:
321
+ value: true
322
+ local_rank:
323
+ value: 0
324
+ log_level:
325
+ value: passive
326
+ log_level_replica:
327
+ value: warning
328
+ log_on_each_node:
329
+ value: true
330
+ logging_dir:
331
+ value: ./models/bert-multilingual-data2/logs
332
+ logging_first_step:
333
+ value: true
334
+ logging_nan_inf_filter:
335
+ value: true
336
+ logging_steps:
337
+ value: 50
338
+ logging_strategy:
339
+ value: steps
340
+ lr_scheduler_type:
341
+ value: linear
342
+ max_grad_norm:
343
+ value: 1
344
+ max_length:
345
+ value: 20
346
+ max_position_embeddings:
347
+ value: 512
348
+ max_steps:
349
+ value: -1
350
+ metric_for_best_model:
351
+ value: f1
352
+ min_length:
353
+ value: 0
354
+ model:
355
+ value: bert-base-multilingual-cased
356
+ model/num_parameters:
357
+ value: 177266693
358
+ model_type:
359
+ value: bert
360
+ mp_parameters:
361
+ value: ""
362
+ neftune_noise_alpha:
363
+ value: null
364
+ no_cuda:
365
+ value: false
366
+ no_repeat_ngram_size:
367
+ value: 0
368
+ num_attention_heads:
369
+ value: 12
370
+ num_beam_groups:
371
+ value: 1
372
+ num_beams:
373
+ value: 1
374
+ num_hidden_layers:
375
+ value: 12
376
+ num_return_sequences:
377
+ value: 1
378
+ num_train_epochs:
379
+ value: 3
380
+ optim:
381
+ value: adamw_torch_fused
382
+ optim_args:
383
+ value: null
384
+ optim_target_modules:
385
+ value: null
386
+ output_attentions:
387
+ value: false
388
+ output_dir:
389
+ value: ./models/bert-multilingual-data2
390
+ output_hidden_states:
391
+ value: false
392
+ output_scores:
393
+ value: false
394
+ overwrite_output_dir:
395
+ value: true
396
+ pad_token_id:
397
+ value: 0
398
+ parallelism_config:
399
+ value: null
400
+ past_index:
401
+ value: -1
402
+ per_device_eval_batch_size:
403
+ value: 32
404
+ per_device_train_batch_size:
405
+ value: 16
406
+ per_gpu_eval_batch_size:
407
+ value: null
408
+ per_gpu_train_batch_size:
409
+ value: null
410
+ pooler_fc_size:
411
+ value: 768
412
+ pooler_num_attention_heads:
413
+ value: 12
414
+ pooler_num_fc_layers:
415
+ value: 3
416
+ pooler_size_per_head:
417
+ value: 128
418
+ pooler_type:
419
+ value: first_token_transform
420
+ position_embedding_type:
421
+ value: absolute
422
+ prediction_loss_only:
423
+ value: false
424
+ prefix:
425
+ value: null
426
+ problem_type:
427
+ value: null
428
+ project:
429
+ value: huggingface
430
+ push_to_hub:
431
+ value: true
432
+ push_to_hub_model_id:
433
+ value: guj-eng-code-switch-bert-multilingual-data2
434
+ push_to_hub_organization:
435
+ value: null
436
+ push_to_hub_token:
437
+ value: <PUSH_TO_HUB_TOKEN>
438
+ ray_scope:
439
+ value: last
440
+ remove_invalid_values:
441
+ value: false
442
+ remove_unused_columns:
443
+ value: true
444
+ repetition_penalty:
445
+ value: 1
446
+ report_to:
447
+ value:
448
+ - tensorboard
449
+ - wandb
450
+ restore_callback_states_from_checkpoint:
451
+ value: false
452
+ resume_from_checkpoint:
453
+ value: null
454
+ return_dict:
455
+ value: true
456
+ return_dict_in_generate:
457
+ value: false
458
+ run_name:
459
+ value: null
460
+ save_on_each_node:
461
+ value: false
462
+ save_only_model:
463
+ value: false
464
+ save_safetensors:
465
+ value: true
466
+ save_steps:
467
+ value: null
468
+ save_strategy:
469
+ value: epoch
470
+ save_total_limit:
471
+ value: 3
472
+ seed:
473
+ value: 42
474
+ sep_token_id:
475
+ value: null
476
+ skip_memory_metrics:
477
+ value: true
478
+ suppress_tokens:
479
+ value: null
480
+ task_specific_params:
481
+ value: null
482
+ temperature:
483
+ value: 1
484
+ tf_legacy_loss:
485
+ value: false
486
+ tf32:
487
+ value: null
488
+ tie_encoder_decoder:
489
+ value: false
490
+ tie_word_embeddings:
491
+ value: true
492
+ tokenizer_class:
493
+ value: null
494
+ top_k:
495
+ value: 50
496
+ top_p:
497
+ value: 1
498
+ torch_compile:
499
+ value: false
500
+ torch_compile_backend:
501
+ value: null
502
+ torch_compile_mode:
503
+ value: null
504
+ torch_empty_cache_steps:
505
+ value: null
506
+ torchdynamo:
507
+ value: null
508
+ torchscript:
509
+ value: false
510
+ tpu_metrics_debug:
511
+ value: false
512
+ tpu_num_cores:
513
+ value: null
514
+ trackio_space_id:
515
+ value: trackio
516
+ train_file:
517
+ value: synthetic_data_gen/data2/train.txt
518
+ transformers_version:
519
+ value: 4.57.1
520
+ type_vocab_size:
521
+ value: 2
522
+ typical_p:
523
+ value: 1
524
+ use_bfloat16:
525
+ value: false
526
+ use_cache:
527
+ value: true
528
+ use_cpu:
529
+ value: false
530
+ use_legacy_prediction_loop:
531
+ value: false
532
+ use_liger_kernel:
533
+ value: false
534
+ use_mps_device:
535
+ value: false
536
+ vocab_size:
537
+ value: 119547
538
+ warmup_ratio:
539
+ value: 0.1
540
+ warmup_steps:
541
+ value: 0
542
+ weight_decay:
543
+ value: 0.01
wandb_logs/run-20251122_173629-7f2wzkw5/files/output.log ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|
3
+ _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|
4
+ _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|
5
+ _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|
6
+ _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|
7
+ Enter your token (input will not be visible):
8
+
9
+ Cannot authenticate through git-credential as no helper is defined on your machine.
10
+ You might have to re-authenticate when pushing to the Hugging Face Hub.
11
+ Run the following command in your terminal in case you want to set the 'store' credential helper as default.
12
+
13
+ git config --global credential.helper store
14
+
15
+ Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.
16
+ Token has not been saved to git credential helper.
17
+ WARNING:huggingface_hub._login:Token has not been saved to git credential helper.
18
+ tokenizer_config.json: 100% 49.0/49.0 [00:00<00:00, 214kB/s]
19
+ config.json: 100% 625/625 [00:00<00:00, 2.74MB/s]
20
+ vocab.txt: 100% 996k/996k [00:00<00:00, 1.59MB/s]
21
+ tokenizer.json: 100% 1.96M/1.96M [00:00<00:00, 4.44MB/s]
22
+ model.safetensors: 100% 714M/714M [00:06<00:00, 113MB/s]
23
+ Some weights of BertForTokenClassification were not initialized from the model checkpoint at bert-base-multilingual-cased and are newly initialized: ['classifier.bias', 'classifier.weight']
24
+ You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
25
+ Downloading builder script: 6.34kB [00:00, 8.22MB/s]
26
+ {'loss': 1.6736, 'grad_norm': 9.364067077636719, 'learning_rate': 0.0, 'epoch': 0.0}
27
+ {'loss': 1.1254, 'grad_norm': 10.865610122680664, 'learning_rate': 1.3066666666666668e-05, 'epoch': 0.2}
28
+ {'loss': 0.3817, 'grad_norm': 3.5892016887664795, 'learning_rate': 1.928888888888889e-05, 'epoch': 0.4}
29
+ {'loss': 0.1743, 'grad_norm': 5.089068412780762, 'learning_rate': 1.780740740740741e-05, 'epoch': 0.6}
30
+ {'loss': 0.1315, 'grad_norm': 2.536372423171997, 'learning_rate': 1.632592592592593e-05, 'epoch': 0.8}
31
+ {'loss': 0.0932, 'grad_norm': 2.548548698425293, 'learning_rate': 1.4844444444444445e-05, 'epoch': 1.0}
32
+ 100% 750/750 [04:59<00:00, 2.50it/s]
33
+ Processing Files (3 / 3) : 100% 709M/709M [00:29<00:00, 24.4MB/s, 5.22MB/s ]
34
+ {'eval_loss': 0.10810670256614685, 'eval_precision': 0.9037234042553192, 'eval_recall': 0.9208672086720867, 'eval_f1': 0.9122147651006711, 'eval_accuracy': 0.970992733169179, 'eval_runtime': 5.4132, 'eval_samples_per_second': 92.367, 'eval_steps_per_second': 2.956, 'epoch': 1.0}
35
+ {'loss': 0.0745, 'grad_norm': 1.2293448448181152, 'learning_rate': 1.3362962962962964e-05, 'epoch': 1.2}
36
+ {'loss': 0.0569, 'grad_norm': 2.833926200866699, 'learning_rate': 1.1881481481481482e-05, 'epoch': 1.4}
37
+ {'loss': 0.0776, 'grad_norm': 2.0456528663635254, 'learning_rate': 1.04e-05, 'epoch': 1.6}
38
+ {'loss': 0.0641, 'grad_norm': 2.135941743850708, 'learning_rate': 8.91851851851852e-06, 'epoch': 1.8}
39
+ {'loss': 0.0758, 'grad_norm': 2.974154233932495, 'learning_rate': 7.437037037037038e-06, 'epoch': 2.0}
40
+ {'eval_loss': 0.09071356058120728, 'eval_precision': 0.9241047568145376, 'eval_recall': 0.9371273712737127, 'eval_f1': 0.9305705059203444, 'eval_accuracy': 0.977658999459492, 'eval_runtime': 4.4008, 'eval_samples_per_second': 113.615, 'eval_steps_per_second': 3.636, 'epoch': 2.0}
41
+ {'loss': 0.0509, 'grad_norm': 0.6356647610664368, 'learning_rate': 5.955555555555555e-06, 'epoch': 2.2}
42
+ {'loss': 0.0473, 'grad_norm': 2.004117727279663, 'learning_rate': 4.4740740740740746e-06, 'epoch': 2.4}
43
+ {'loss': 0.0354, 'grad_norm': 0.2392495572566986, 'learning_rate': 2.992592592592593e-06, 'epoch': 2.6}
44
+ {'loss': 0.0317, 'grad_norm': 1.2536988258361816, 'learning_rate': 1.5111111111111112e-06, 'epoch': 2.8}
45
+ {'loss': 0.0348, 'grad_norm': 1.0227235555648804, 'learning_rate': 2.9629629629629632e-08, 'epoch': 3.0}
46
+ {'eval_loss': 0.09460805356502533, 'eval_precision': 0.927038626609442, 'eval_recall': 0.9365853658536586, 'eval_f1': 0.9317875438123484, 'eval_accuracy': 0.9788000720677437, 'eval_runtime': 4.3756, 'eval_samples_per_second': 114.271, 'eval_steps_per_second': 3.657, 'epoch': 3.0}
47
+ {'train_runtime': 299.4505, 'train_samples_per_second': 40.073, 'train_steps_per_second': 2.505, 'train_loss': 0.16440406481424968, 'epoch': 3.0}
48
+ New Data Upload : 100% 644M/644M [00:29<00:00, 22.2MB/s, 5.22MB/s ]
49
+ ...l-data2/training_args.bin: 100% 5.97k/5.97k [00:28<?, ?B/s]
50
+ ...l-data2/model.safetensors: 100% 709M/709M [00:26<00:00, 26.7MB/s]
51
+ ...33015.8b09dd3d6919.1459.0: 100% 10.6k/10.6k [00:18<00:00, 527B/s]
52
+ Processing Files (3 / 3) : 100% 709M/709M [00:06<00:00, 111MB/s, 109MB/s ]
53
+ New Data Upload : 100% 1.28M/1.28M [00:06<00:00, 200kB/s, 207kB/s ]
54
+ ...l-data2/training_args.bin: 100% 5.97k/5.97k [00:06<?, ?B/s]
55
+ ...33015.8b09dd3d6919.1459.0: 100% 10.6k/10.6k [00:06<?, ?B/s]
56
+ ...l-data2/model.safetensors: 100% 709M/709M [00:06<00:00, 109MB/s]
57
+ No files have been modified since last commit. Skipping to prevent empty commit.
58
+ WARNING:huggingface_hub.hf_api:No files have been modified since last commit. Skipping to prevent empty commit.
59
+ ***** train metrics *****
60
+ epoch = 3.0
61
+ total_flos = 489613GF
62
+ train_loss = 0.1644
63
+ train_runtime = 0:04:59.45
64
+ train_samples_per_second = 40.073
65
+ train_steps_per_second = 2.505
66
+ 100% 16/16 [00:04<00:00, 3.75it/s]
67
+ ***** eval metrics *****
68
+ epoch = 3.0
69
+ eval_accuracy = 0.9788
70
+ eval_f1 = 0.9318
71
+ eval_loss = 0.0946
72
+ eval_precision = 0.927
73
+ eval_recall = 0.9366
74
+ eval_runtime = 0:00:04.44
75
+ eval_samples_per_second = 112.366
76
+ eval_steps_per_second = 3.596
77
+ 100% 16/16 [00:02<00:00, 5.79it/s]early stopping required metric_for_best_model, but did not find eval_f1 so early stopping is disabled
78
+ 100% 16/16 [00:04<00:00, 3.75it/s]
79
+ ***** test metrics *****
80
+ epoch = 3.0
81
+ test_accuracy = 0.9884
82
+ test_f1 = 0.946
83
+ test_loss = 0.0453
84
+ test_precision = 0.9455
85
+ test_recall = 0.9465
86
+ test_runtime = 0:00:04.48
87
+ test_samples_per_second = 111.603
88
+ test_steps_per_second = 3.571
wandb_logs/run-20251122_173629-7f2wzkw5/files/requirements.txt ADDED
@@ -0,0 +1,698 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ setuptools==75.2.0
2
+ pip==24.1.2
3
+ requirements-parser==0.9.0
4
+ types-setuptools==80.9.0.20250822
5
+ ipykernel==7.1.0
6
+ tensorboard==2.20.0
7
+ numpy==2.3.5
8
+ pyarrow==22.0.0
9
+ matplotlib==3.10.7
10
+ widgetsnbextension==4.0.15
11
+ seqeval==1.2.2
12
+ ipywidgets==8.1.8
13
+ datasets==4.4.1
14
+ pandas==2.3.3
15
+ comm==0.2.3
16
+ google-genai==1.50.1
17
+ scikit-learn==1.7.2
18
+ evaluate==0.4.6
19
+ jedi==0.19.2
20
+ jupyter_client==8.6.3
21
+ google-colab==1.0.0
22
+ httpcore==1.0.9
23
+ colorlover==0.3.0
24
+ pyOpenSSL==24.2.1
25
+ PySocks==1.7.1
26
+ fsspec==2025.3.0
27
+ google-ai-generativelanguage==0.6.15
28
+ dlib==19.24.6
29
+ fastdownload==0.0.7
30
+ jaxlib==0.7.2
31
+ python-multipart==0.0.20
32
+ nltk==3.9.1
33
+ chardet==5.2.0
34
+ pyparsing==3.2.5
35
+ sentry-sdk==2.45.0
36
+ audioread==3.1.0
37
+ langchain-core==0.3.80
38
+ jaraco.classes==3.4.0
39
+ cymem==2.0.13
40
+ vega-datasets==0.9.0
41
+ docstring_parser==0.17.0
42
+ nest-asyncio==1.6.0
43
+ mlxtend==0.23.4
44
+ xyzservices==2025.10.0
45
+ more-itertools==10.8.0
46
+ torchao==0.10.0
47
+ numba==0.60.0
48
+ panel==1.8.3
49
+ docutils==0.21.2
50
+ holoviews==1.22.0
51
+ attrs==25.4.0
52
+ db-dtypes==1.4.4
53
+ tabulate==0.9.0
54
+ pydotplus==2.0.2
55
+ soundfile==0.13.1
56
+ sklearn-pandas==2.2.0
57
+ multitasking==0.0.12
58
+ glob2==0.7
59
+ nvidia-cusolver-cu12==11.7.1.2
60
+ google-adk==1.17.0
61
+ alabaster==1.0.0
62
+ mdit-py-plugins==0.5.0
63
+ intel-cmplr-lib-ur==2025.3.1
64
+ nvidia-cufft-cu12==11.3.0.4
65
+ google-cloud-bigquery-connection==1.19.0
66
+ polars==1.31.0
67
+ openai==1.109.1
68
+ google-cloud-spanner==3.59.0
69
+ patsy==1.0.2
70
+ pytest==8.4.2
71
+ pycparser==2.23
72
+ curl_cffi==0.13.0
73
+ linkify-it-py==2.0.3
74
+ imutils==0.5.4
75
+ Markdown==3.10
76
+ pandas-stubs==2.2.2.240909
77
+ pooch==1.8.2
78
+ pandas-gbq==0.30.0
79
+ google-cloud-dataproc==5.23.0
80
+ google-cloud-language==2.18.0
81
+ jupyter_kernel_gateway==2.5.2
82
+ google-resumable-media==2.8.0
83
+ nvidia-cuda-runtime-cu12==12.6.77
84
+ dask-cudf-cu12==25.10.0
85
+ websocket-client==1.9.0
86
+ distributed-ucxx-cu12==0.46.0
87
+ altair==5.5.0
88
+ idna==3.11
89
+ wandb==0.23.0
90
+ moviepy==1.0.3
91
+ click==8.3.1
92
+ oauth2client==4.1.3
93
+ GDAL==3.8.4
94
+ mcp==1.21.2
95
+ pyzmq==26.2.1
96
+ langsmith==0.4.43
97
+ sqlparse==0.5.3
98
+ betterproto==2.0.0b6
99
+ parso==0.8.5
100
+ imbalanced-learn==0.14.0
101
+ tbb==2022.3.0
102
+ dm-tree==0.1.9
103
+ cuda-python==12.9.4
104
+ pygit2==1.19.0
105
+ proglog==0.1.12
106
+ fastjsonschema==2.21.2
107
+ tornado==6.5.1
108
+ matplotlib-venn==1.1.2
109
+ Authlib==1.6.5
110
+ cryptography==43.0.3
111
+ snowballstemmer==3.0.1
112
+ networkx==3.5
113
+ nvidia-cublas-cu12==12.6.4.1
114
+ wcwidth==0.2.14
115
+ dopamine_rl==4.1.2
116
+ blobfile==3.1.0
117
+ simple-parsing==0.1.7
118
+ pylibcugraph-cu12==25.10.1
119
+ sentence-transformers==5.1.2
120
+ jsonpatch==1.33
121
+ webencodings==0.5.1
122
+ zict==3.0.0
123
+ google-cloud-bigquery-storage==2.34.0
124
+ sphinxcontrib-serializinghtml==2.0.0
125
+ uc-micro-py==1.0.3
126
+ rfc3987-syntax==1.1.0
127
+ itsdangerous==2.2.0
128
+ peft==0.18.0
129
+ gspread-dataframe==4.0.0
130
+ pydot==3.0.4
131
+ pydantic_core==2.33.2
132
+ oauthlib==3.3.1
133
+ google-cloud-bigquery==3.38.0
134
+ geopy==2.4.1
135
+ rmm-cu12==25.10.0
136
+ distributed==2025.9.1
137
+ pandocfilters==1.5.1
138
+ llvmlite==0.43.0
139
+ torchaudio==2.9.0+cu126
140
+ hdbscan==0.8.40
141
+ safetensors==0.7.0
142
+ et_xmlfile==2.0.0
143
+ numexpr==2.14.1
144
+ scs==3.2.9
145
+ importlib_resources==6.5.2
146
+ pyogrio==0.11.1
147
+ rapids-logger==0.1.19
148
+ google==2.0.3
149
+ blinker==1.9.0
150
+ colour==0.1.5
151
+ lightgbm==4.6.0
152
+ pylibraft-cu12==25.10.0
153
+ autograd==1.8.0
154
+ duckdb==1.3.2
155
+ typing_extensions==4.15.0
156
+ protobuf==5.29.5
157
+ argon2-cffi==25.1.0
158
+ Bottleneck==1.4.2
159
+ libucxx-cu12==0.46.0
160
+ libcugraph-cu12==25.10.1
161
+ huggingface-hub==0.36.0
162
+ fastapi==0.121.3
163
+ mistune==3.1.4
164
+ pyspark==3.5.1
165
+ ibis-framework==9.5.0
166
+ tqdm==4.67.1
167
+ seaborn==0.13.2
168
+ mdurl==0.1.2
169
+ stumpy==1.13.0
170
+ python-dotenv==1.2.1
171
+ psygnal==0.15.0
172
+ music21==9.3.0
173
+ Farama-Notifications==0.0.4
174
+ jsonschema-specifications==2025.9.1
175
+ xxhash==3.6.0
176
+ confection==0.1.5
177
+ treelite==4.4.1
178
+ httpimport==1.4.1
179
+ libpysal==4.13.0
180
+ cramjam==2.11.0
181
+ google-cloud-functions==1.21.0
182
+ grpcio-status==1.71.2
183
+ torchsummary==1.5.1
184
+ nvidia-nvshmem-cu12==3.3.20
185
+ libucx-cu12==1.19.0
186
+ geopandas==1.1.1
187
+ toml==0.10.2
188
+ shapely==2.1.2
189
+ html5lib==1.1
190
+ antlr4-python3-runtime==4.9.3
191
+ clarabel==0.11.1
192
+ uvicorn==0.38.0
193
+ toolz==0.12.1
194
+ cloudpathlib==0.23.0
195
+ cupy-cuda12x==13.6.0
196
+ fastai==2.8.5
197
+ peewee==3.18.3
198
+ GitPython==3.1.45
199
+ aiohappyeyeballs==2.6.1
200
+ murmurhash==1.0.15
201
+ jax-cuda12-plugin==0.7.2
202
+ pyperclip==1.11.0
203
+ promise==2.3
204
+ jupyter_server==2.14.0
205
+ webcolors==25.10.0
206
+ imagesize==1.4.1
207
+ prettytable==3.17.0
208
+ alembic==1.17.2
209
+ progressbar2==4.5.0
210
+ requests==2.32.4
211
+ nvidia-ml-py==13.580.82
212
+ humanize==4.14.0
213
+ umap-learn==0.5.9.post2
214
+ h5netcdf==1.7.3
215
+ PyGObject==3.42.0
216
+ google-cloud-aiplatform==1.128.0
217
+ flatbuffers==25.9.23
218
+ optax==0.2.6
219
+ nvidia-cuda-cupti-cu12==12.6.80
220
+ nx-cugraph-cu12==25.10.0
221
+ lark==1.3.1
222
+ tenacity==8.5.0
223
+ entrypoints==0.4
224
+ prompt_toolkit==3.0.52
225
+ fonttools==4.60.1
226
+ ffmpy==1.0.0
227
+ google-cloud-core==2.5.0
228
+ matplotlib-inline==0.2.1
229
+ sphinxcontrib-jsmath==1.0.1
230
+ ply==3.11
231
+ tweepy==4.16.0
232
+ en_core_web_sm==3.8.0
233
+ google-crc32c==1.7.1
234
+ libcudf-cu12==25.10.0
235
+ ipytree==0.2.2
236
+ ImageIO==2.37.2
237
+ rfc3339-validator==0.1.4
238
+ keras==3.10.0
239
+ opt_einsum==3.4.0
240
+ jupyter_server_terminals==0.5.3
241
+ rpds-py==0.29.0
242
+ threadpoolctl==3.6.0
243
+ urllib3==2.5.0
244
+ kagglehub==0.3.13
245
+ Flask==3.1.2
246
+ easydict==1.13
247
+ grpcio==1.76.0
248
+ ratelim==0.1.6
249
+ logical-unification==0.4.7
250
+ omegaconf==2.3.0
251
+ roman-numerals-py==3.1.0
252
+ dataproc-spark-connect==0.8.3
253
+ langchain-text-splitters==0.3.11
254
+ tinycss2==1.4.0
255
+ python-json-logger==4.0.0
256
+ scikit-image==0.25.2
257
+ highspy==1.12.0
258
+ tf-slim==1.1.0
259
+ torchtune==0.6.1
260
+ jupyter-console==6.6.3
261
+ spanner-graph-notebook==1.1.8
262
+ dill==0.3.8
263
+ tensorboard-data-server==0.7.2
264
+ slicer==0.0.8
265
+ keyring==25.7.0
266
+ arviz==0.22.0
267
+ sympy==1.13.3
268
+ google-cloud-resource-manager==1.15.0
269
+ traittypes==0.2.3
270
+ typer-slim==0.20.0
271
+ annotated-doc==0.0.4
272
+ hf-xet==1.2.0
273
+ dask-cuda==25.10.0
274
+ pymc==5.26.1
275
+ pynndescent==0.5.13
276
+ stanio==0.5.1
277
+ treescope==0.1.10
278
+ optree==0.18.0
279
+ propcache==0.4.1
280
+ rich==13.9.4
281
+ gcsfs==2025.3.0
282
+ torch==2.9.0+cu126
283
+ MarkupSafe==3.0.3
284
+ tzlocal==5.3.1
285
+ google-cloud-secret-manager==2.25.0
286
+ atpublic==5.1
287
+ gitdb==4.0.12
288
+ ruff==0.14.5
289
+ opentelemetry-exporter-gcp-monitoring==1.11.0a0
290
+ grpc-interceptor==0.15.4
291
+ opentelemetry-exporter-gcp-logging==1.11.0a0
292
+ fqdn==1.5.1
293
+ soxr==1.0.0
294
+ hf_transfer==0.1.9
295
+ pyasn1==0.6.1
296
+ geemap==0.35.3
297
+ regex==2024.11.6
298
+ ipython-sql==0.5.0
299
+ pyviz_comms==3.0.6
300
+ pydub==0.25.1
301
+ geographiclib==2.1
302
+ Jinja2==3.1.6
303
+ ipython-genutils==0.2.0
304
+ multiprocess==0.70.16
305
+ h11==0.16.0
306
+ tables==3.10.2
307
+ tensorflow-text==2.19.0
308
+ bokeh==3.7.3
309
+ opentelemetry-resourcedetector-gcp==1.11.0a0
310
+ beautifulsoup4==4.13.5
311
+ filelock==3.20.0
312
+ catalogue==2.0.10
313
+ fasttransform==0.0.2
314
+ typeguard==4.4.4
315
+ openpyxl==3.1.5
316
+ tokenizers==0.22.1
317
+ plotly==5.24.1
318
+ ucxx-cu12==0.46.0
319
+ branca==0.8.2
320
+ overrides==7.7.0
321
+ cuda-core==0.3.2
322
+ tensorflow-probability==0.25.0
323
+ xarray-einstats==0.9.1
324
+ tf_keras==2.19.0
325
+ referencing==0.37.0
326
+ argon2-cffi-bindings==25.1.0
327
+ librmm-cu12==25.10.0
328
+ nvidia-cusparse-cu12==12.5.4.2
329
+ google-cloud-discoveryengine==0.13.12
330
+ xgboost==3.1.1
331
+ diffusers==0.35.2
332
+ timm==1.0.22
333
+ PyDrive2==1.21.3
334
+ tblib==3.2.2
335
+ scooby==0.11.0
336
+ opencv-python-headless==4.12.0.88
337
+ wheel==0.45.1
338
+ firebase-admin==6.9.0
339
+ shap==0.50.0
340
+ jsonpointer==3.0.0
341
+ python-louvain==0.16
342
+ charset-normalizer==3.4.4
343
+ sqlglot==25.20.2
344
+ jsonschema==4.25.1
345
+ jieba==0.42.1
346
+ importlib_metadata==8.7.0
347
+ nvidia-cuda-nvrtc-cu12==12.6.77
348
+ editdistance==0.8.1
349
+ jax==0.7.2
350
+ google-api-core==2.28.1
351
+ shellingham==1.5.4
352
+ portpicker==1.5.2
353
+ cudf-cu12==25.10.0
354
+ gspread==6.2.1
355
+ pylibcudf-cu12==25.10.0
356
+ python-slugify==8.0.4
357
+ anywidget==0.9.21
358
+ distro==1.9.0
359
+ stringzilla==4.2.3
360
+ libcuml-cu12==25.10.0
361
+ graphviz==0.21
362
+ ipython==7.34.0
363
+ hyperopt==0.2.7
364
+ sniffio==1.3.1
365
+ python-utils==3.9.1
366
+ bigframes==2.29.1
367
+ folium==0.20.0
368
+ google-cloud-bigtable==2.34.0
369
+ text-unidecode==1.3
370
+ pydantic-settings==2.12.0
371
+ annotated-types==0.7.0
372
+ locket==1.0.0
373
+ pyproj==3.7.2
374
+ orbax-checkpoint==0.11.28
375
+ PyJWT==2.10.1
376
+ natsort==8.4.0
377
+ astropy-iers-data==0.2025.11.10.0.38.31
378
+ gym-notices==0.1.0
379
+ debugpy==1.8.15
380
+ weasel==0.4.3
381
+ PyOpenGL==3.1.10
382
+ pydata-google-auth==1.9.1
383
+ semantic-version==2.10.0
384
+ google-cloud-firestore==2.21.0
385
+ statsmodels==0.14.5
386
+ pycocotools==2.0.10
387
+ greenlet==3.2.4
388
+ Werkzeug==3.1.3
389
+ preshed==3.0.12
390
+ gymnasium==1.2.2
391
+ prometheus_client==0.23.1
392
+ triton==3.5.0
393
+ frozendict==2.4.7
394
+ multipledispatch==1.0.0
395
+ srsly==2.5.2
396
+ google-auth-httplib2==0.2.1
397
+ zstandard==0.25.0
398
+ uri-template==1.3.0
399
+ gradio==5.49.1
400
+ websockets==15.0.1
401
+ bigquery-magics==0.10.3
402
+ nvidia-cuda-nvcc-cu12==12.5.82
403
+ etils==1.13.0
404
+ cufflinks==0.17.3
405
+ simsimd==6.5.3
406
+ frozenlist==1.8.0
407
+ transformers==4.57.1
408
+ ale-py==0.11.2
409
+ orjson==3.11.4
410
+ jiter==0.12.0
411
+ safehttpx==0.1.7
412
+ google-auth==2.38.0
413
+ inflect==7.5.0
414
+ decorator==4.4.2
415
+ types-pytz==2025.2.0.20251108
416
+ cyipopt==1.5.0
417
+ imageio-ffmpeg==0.6.0
418
+ pyshp==3.0.2.post1
419
+ grpc-google-iam-v1==0.14.3
420
+ immutabledict==4.2.2
421
+ ipyparallel==8.8.0
422
+ beartype==0.22.5
423
+ keras-nlp==0.21.1
424
+ tensorflow-hub==0.16.1
425
+ yfinance==0.2.66
426
+ cuda-toolkit==12.9.1
427
+ googleapis-common-protos==1.72.0
428
+ google-generativeai==0.8.5
429
+ aiofiles==24.1.0
430
+ joblib==1.5.2
431
+ ndindex==1.10.1
432
+ nbformat==5.10.4
433
+ pygame==2.6.1
434
+ opentelemetry-proto==1.37.0
435
+ cachetools==5.5.2
436
+ sphinxcontrib-qthelp==2.0.0
437
+ albumentations==2.0.8
438
+ libraft-cu12==25.10.0
439
+ absl-py==1.4.0
440
+ simplejson==3.20.2
441
+ jupytext==1.17.3
442
+ raft-dask-cu12==25.10.0
443
+ pyomo==6.9.5
444
+ msgpack==1.1.2
445
+ tensorflow==2.19.0
446
+ dask==2025.9.1
447
+ aiohttp==3.13.2
448
+ future==1.0.0
449
+ bleach==6.3.0
450
+ cmdstanpy==1.3.0
451
+ wurlitzer==3.1.1
452
+ libkvikio-cu12==25.10.0
453
+ google-cloud-audit-log==0.4.0
454
+ packaging==25.0
455
+ defusedxml==0.7.1
456
+ google-auth-oauthlib==1.2.3
457
+ textblob==0.19.0
458
+ pexpect==4.9.0
459
+ Mako==1.3.10
460
+ cmake==3.31.6
461
+ eerepr==0.1.2
462
+ namex==0.1.0
463
+ sse-starlette==3.0.3
464
+ grpclib==0.4.8
465
+ jaraco.context==6.0.1
466
+ nbclient==0.10.2
467
+ scipy==1.16.3
468
+ miniKanren==1.0.5
469
+ nvidia-curand-cu12==10.3.7.77
470
+ sphinxcontrib-applehelp==2.0.0
471
+ python-dateutil==2.9.0.post0
472
+ librosa==0.11.0
473
+ ptyprocess==0.7.0
474
+ opentelemetry-api==1.37.0
475
+ nvtx==0.2.13
476
+ nvidia-cufile-cu12==1.11.1.6
477
+ plum-dispatch==2.6.0
478
+ kiwisolver==1.4.9
479
+ ipyleaflet==0.20.0
480
+ jaraco.functools==4.3.0
481
+ terminado==0.18.1
482
+ tensorflow_decision_forests==1.12.0
483
+ Send2Trash==1.8.3
484
+ flax==0.10.7
485
+ PyWavelets==1.9.0
486
+ brotli==1.2.0
487
+ mpmath==1.3.0
488
+ earthengine-api==1.5.24
489
+ isoduration==20.11.0
490
+ pytz==2025.2
491
+ tiktoken==0.12.0
492
+ traitlets==5.7.1
493
+ typer==0.20.0
494
+ plotnine==0.14.5
495
+ sphinxcontrib-devhelp==2.0.0
496
+ spacy==3.8.11
497
+ gym==0.25.2
498
+ google-cloud-datastore==2.21.0
499
+ torchdata==0.11.0
500
+ bqplot==0.12.45
501
+ missingno==0.5.2
502
+ nvidia-cudnn-cu12==9.10.2.21
503
+ param==2.3.0
504
+ tensorstore==0.1.79
505
+ ipyfilechooser==0.6.0
506
+ rfc3986-validator==0.1.1
507
+ nibabel==5.3.2
508
+ starlette==0.50.0
509
+ psutil==5.9.5
510
+ lazy_loader==0.4
511
+ smart_open==7.5.0
512
+ jupyter_core==5.9.1
513
+ pycairo==1.29.0
514
+ pytensor==2.35.1
515
+ hpack==4.1.0
516
+ smmap==5.0.2
517
+ httplib2==0.31.0
518
+ h2==4.3.0
519
+ nvidia-nccl-cu12==2.27.5
520
+ googledrivedownloader==1.1.0
521
+ SQLAlchemy==2.0.44
522
+ yellowbrick==1.5
523
+ cloudpickle==3.1.2
524
+ typing-inspection==0.4.2
525
+ cuml-cu12==25.10.0
526
+ tensorflow-metadata==1.17.2
527
+ hyperframe==6.1.0
528
+ numba-cuda==0.19.1
529
+ rpy2==3.5.17
530
+ cuda-bindings==12.9.4
531
+ langchain==0.3.27
532
+ array_record==0.8.3
533
+ google-cloud-appengine-logging==1.7.0
534
+ requests-oauthlib==2.0.0
535
+ lxml==5.4.0
536
+ rsa==4.9.1
537
+ thinc==8.3.10
538
+ tomlkit==0.13.3
539
+ blis==1.3.3
540
+ opentelemetry-sdk==1.37.0
541
+ kaggle==1.7.4.5
542
+ tcmlib==1.4.1
543
+ holidays==0.85
544
+ multidict==6.7.0
545
+ accelerate==1.11.0
546
+ pyerfa==2.0.1.5
547
+ babel==2.17.0
548
+ google-api-python-client==2.187.0
549
+ cffi==2.0.0
550
+ soupsieve==2.8
551
+ opencv-python==4.12.0.88
552
+ rapids-dask-dependency==25.10.0
553
+ chex==0.1.90
554
+ google-cloud-translate==3.23.0
555
+ python-snappy==0.7.3
556
+ xarray==2025.11.0
557
+ pillow==11.3.0
558
+ uritemplate==4.2.0
559
+ Cython==3.0.12
560
+ tensorflow-datasets==4.9.9
561
+ mkl==2025.2.0
562
+ cvxpy==1.6.7
563
+ spacy-loggers==1.0.5
564
+ keyrings.google-artifactregistry-auth==1.1.2
565
+ spacy-legacy==3.0.12
566
+ fastrlock==0.8.3
567
+ aiosignal==1.4.0
568
+ osqp==1.0.5
569
+ astunparse==1.6.3
570
+ py-cpuinfo==9.0.0
571
+ nbclassic==1.3.3
572
+ pycryptodomex==3.23.0
573
+ anyio==4.11.0
574
+ ydf==0.13.0
575
+ parsy==2.2
576
+ einops==0.8.1
577
+ iniconfig==2.3.0
578
+ cycler==0.12.1
579
+ h5py==3.15.1
580
+ libclang==18.1.1
581
+ gdown==5.2.0
582
+ wasabi==1.1.3
583
+ httpx==0.28.1
584
+ termcolor==3.2.0
585
+ umf==1.0.2
586
+ mizani==0.13.5
587
+ astropy==7.1.1
588
+ opentelemetry-exporter-gcp-trace==1.11.0
589
+ pandas-datareader==0.10.0
590
+ nvidia-nvjitlink-cu12==12.6.85
591
+ pickleshare==0.7.5
592
+ community==1.0.0b1
593
+ prophet==1.1.7
594
+ jupyterlab_pygments==0.3.0
595
+ requests-toolbelt==1.0.0
596
+ gradio_client==1.13.3
597
+ pydantic==2.11.10
598
+ google-cloud-logging==3.12.1
599
+ google-cloud-storage==2.19.0
600
+ intel-openmp==2025.3.1
601
+ tifffile==2025.10.16
602
+ colorcet==3.1.0
603
+ google-cloud-speech==2.34.0
604
+ notebook_shim==0.2.4
605
+ xlrd==2.0.2
606
+ httpx-sse==0.4.3
607
+ backcall==0.2.0
608
+ blosc2==3.11.1
609
+ sortedcontainers==2.4.0
610
+ opentelemetry-exporter-otlp-proto-common==1.37.0
611
+ sentencepiece==0.2.1
612
+ six==1.17.0
613
+ google-pasta==0.2.0
614
+ sphinxcontrib-htmlhelp==2.1.0
615
+ zipp==3.23.0
616
+ jupyter-leaflet==0.20.0
617
+ jeepney==0.9.0
618
+ cons==0.4.7
619
+ markdown-it-py==4.0.0
620
+ wordcloud==1.9.4
621
+ opencv-contrib-python==4.12.0.88
622
+ opentelemetry-exporter-otlp-proto-http==1.37.0
623
+ absolufy-imports==0.3.1
624
+ psycopg2==2.9.11
625
+ groovy==0.1.2
626
+ CacheControl==0.14.4
627
+ arrow==1.4.0
628
+ ipyevents==2.0.4
629
+ tzdata==2025.2
630
+ nvidia-nvtx-cu12==12.6.77
631
+ Sphinx==8.2.3
632
+ tsfresh==0.21.1
633
+ jupyter-events==0.12.0
634
+ partd==1.4.2
635
+ platformdirs==4.5.0
636
+ SecretStorage==3.4.1
637
+ narwhals==2.12.0
638
+ sqlalchemy-spanner==1.17.1
639
+ watchdog==6.0.0
640
+ nbconvert==7.16.6
641
+ google-cloud-trace==1.17.0
642
+ cuda-pathfinder==1.3.2
643
+ proto-plus==1.26.1
644
+ notebook==6.5.7
645
+ fastcore==1.8.16
646
+ pluggy==1.6.0
647
+ etuples==0.3.10
648
+ gast==0.6.0
649
+ PyYAML==6.0.3
650
+ opentelemetry-semantic-conventions==0.58b0
651
+ ml_dtypes==0.5.4
652
+ google-cloud-monitoring==2.28.0
653
+ pyasn1_modules==0.4.2
654
+ cvxopt==1.3.2
655
+ contourpy==1.3.3
656
+ gin-config==0.5.0
657
+ certifi==2025.11.12
658
+ jsonpickle==4.1.1
659
+ wrapt==2.0.1
660
+ keras-hub==0.21.1
661
+ torchvision==0.24.0+cu126
662
+ yarl==1.22.0
663
+ jupyterlab_widgets==3.0.16
664
+ py4j==0.10.9.7
665
+ Pygments==2.19.2
666
+ python-box==7.3.2
667
+ albucore==0.0.24
668
+ nvidia-cuda-cccl-cu12==12.9.27
669
+ jax-cuda12-pjrt==0.7.2
670
+ fastprogress==1.0.3
671
+ nvidia-cusparselt-cu12==0.7.1
672
+ geocoder==1.38.1
673
+ cudf-polars-cu12==25.10.0
674
+ python-apt==0.0.0
675
+ httplib2==0.20.2
676
+ more-itertools==8.10.0
677
+ oauthlib==3.2.0
678
+ pyparsing==2.4.7
679
+ PyGObject==3.42.1
680
+ lazr.restfulclient==0.14.4
681
+ lazr.uri==1.0.6
682
+ PyJWT==2.3.0
683
+ blinker==1.4
684
+ python-apt==2.4.0+ubuntu4
685
+ launchpadlib==1.10.16
686
+ six==1.16.0
687
+ zipp==1.0.0
688
+ importlib-metadata==4.6.4
689
+ dbus-python==1.2.18
690
+ wadllib==1.3.6
691
+ cryptography==3.4.8
692
+ distro==1.7.0
693
+ keyring==23.5.0
694
+ SecretStorage==3.3.1
695
+ jeepney==0.7.1
696
+ Markdown==3.3.6
697
+ Mako==1.1.3
698
+ MarkupSafe==2.0.1
wandb_logs/run-20251122_173629-7f2wzkw5/files/wandb-metadata.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.6.105+-x86_64-with-glibc2.35",
3
+ "python": "CPython 3.12.12",
4
+ "startedAt": "2025-11-22T17:36:29.567968Z",
5
+ "args": [
6
+ "configs/bert_data2.json"
7
+ ],
8
+ "program": "/content/code-switch-identification-model/train.py",
9
+ "codePath": "train.py",
10
+ "codePathLocal": "train.py",
11
+ "git": {
12
+ "remote": "https://h3110Fr13nd:@github.com/h3110Fr13nd/code-switch-identification-model.git",
13
+ "commit": "c280afc6ba26ad46a6cf9a434272dbf927fafc80"
14
+ },
15
+ "email": "vijaysinghkushwaha3737@gmail.com",
16
+ "root": "/content/code-switch-identification-model",
17
+ "host": "8b09dd3d6919",
18
+ "executable": "/usr/bin/python3",
19
+ "cpu_count": 1,
20
+ "cpu_count_logical": 2,
21
+ "gpu": "Tesla T4",
22
+ "gpu_count": 1,
23
+ "disk": {
24
+ "/": {
25
+ "total": "120942624768",
26
+ "used": "41433153536"
27
+ }
28
+ },
29
+ "memory": {
30
+ "total": "13605851136"
31
+ },
32
+ "gpu_nvidia": [
33
+ {
34
+ "name": "Tesla T4",
35
+ "memoryTotal": "16106127360",
36
+ "cudaCores": 2560,
37
+ "architecture": "Turing",
38
+ "uuid": "GPU-1b701237-0e57-cd79-3d08-bb01f3fff16f"
39
+ }
40
+ ],
41
+ "cudaVersion": "12.4",
42
+ "writerId": "zyfw9xtja269bha0ppac3mxoy5904j9p"
43
+ }
wandb_logs/run-20251122_173629-7f2wzkw5/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"test/accuracy":0.9884382566585956,"test/steps_per_second":3.571,"train/learning_rate":2.9629629629629632e-08,"train_steps_per_second":2.505,"train/loss":0.0348,"train_samples_per_second":40.073,"eval/steps_per_second":3.596,"test/precision":0.9454937938478144,"train/epoch":3,"eval/runtime":4.4498,"eval/samples_per_second":112.366,"test/recall":0.946515397082658,"train/global_step":750,"_runtime":415,"test/loss":0.04531445354223251,"test/f1":0.9460043196544277,"eval/f1":0.9317875438123484,"_step":21,"total_flos":5.2571883657072e+14,"eval/recall":0.9365853658536586,"train_runtime":299.4505,"test/runtime":4.4802,"eval/precision":0.927038626609442,"test/samples_per_second":111.603,"train/grad_norm":1.0227235555648804,"eval/loss":0.09460805356502533,"_wandb":{"runtime":415},"_timestamp":1.763833407004338e+09,"train_loss":0.16440406481424968,"eval/accuracy":0.9788000720677437}
wandb_logs/run-20251122_173629-7f2wzkw5/logs/debug-core.log ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-11-22T17:36:30.165217048Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpeym5nhp6/port-1459.txt","pid":1459,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2025-11-22T17:36:30.167187839Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1459-1649-3620678407/socket","Net":"unix"}}
3
+ {"time":"2025-11-22T17:36:30.167304013Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1459}
4
+ {"time":"2025-11-22T17:36:30.292606512Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2025-11-22T17:36:30.309708276Z","level":"INFO","msg":"handleInformInit: received","streamId":"7f2wzkw5","id":"1(@)"}
6
+ {"time":"2025-11-22T17:36:30.659242282Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"7f2wzkw5","id":"1(@)"}
7
+ {"time":"2025-11-22T17:43:28.79831427Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"7f2wzkw5","id":"1(@)"}
8
+ {"time":"2025-11-22T17:43:28.803820639Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"7f2wzkw5","id":"1(@)"}
9
+ {"time":"2025-11-22T17:43:34.775059706Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
10
+ {"time":"2025-11-22T17:43:34.775111457Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
11
+ {"time":"2025-11-22T17:43:34.775121642Z","level":"INFO","msg":"server is shutting down"}
12
+ {"time":"2025-11-22T17:43:34.77520721Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1459-1649-3620678407/socket","Net":"unix"}}
13
+ {"time":"2025-11-22T17:43:34.775249599Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
14
+ {"time":"2025-11-22T17:43:34.775322227Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
15
+ {"time":"2025-11-22T17:43:34.775331049Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
16
+ {"time":"2025-11-22T17:43:34.775342169Z","level":"INFO","msg":"server is closed"}
wandb_logs/run-20251122_173629-7f2wzkw5/logs/debug-internal.log ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-11-22T17:36:30.309809744Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
2
+ {"time":"2025-11-22T17:36:30.658933282Z","level":"INFO","msg":"stream: created new stream","id":"7f2wzkw5"}
3
+ {"time":"2025-11-22T17:36:30.659033035Z","level":"INFO","msg":"handler: started","stream_id":"7f2wzkw5"}
4
+ {"time":"2025-11-22T17:36:30.659231232Z","level":"INFO","msg":"stream: started","id":"7f2wzkw5"}
5
+ {"time":"2025-11-22T17:36:30.659288352Z","level":"INFO","msg":"writer: started","stream_id":"7f2wzkw5"}
6
+ {"time":"2025-11-22T17:36:30.659315281Z","level":"INFO","msg":"sender: started","stream_id":"7f2wzkw5"}
7
+ {"time":"2025-11-22T17:43:28.479276173Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
8
+ {"time":"2025-11-22T17:43:28.793500251Z","level":"INFO","msg":"handler: operation stats","stats":{}}
9
+ {"time":"2025-11-22T17:43:28.80038483Z","level":"INFO","msg":"stream: closing","id":"7f2wzkw5"}
10
+ {"time":"2025-11-22T17:43:28.800412693Z","level":"INFO","msg":"handler: closed","stream_id":"7f2wzkw5"}
11
+ {"time":"2025-11-22T17:43:28.800474018Z","level":"INFO","msg":"sender: closed","stream_id":"7f2wzkw5"}
12
+ {"time":"2025-11-22T17:43:28.800494226Z","level":"INFO","msg":"stream: closed","id":"7f2wzkw5"}
wandb_logs/run-20251122_173629-7f2wzkw5/logs/debug.log ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
2
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_setup.py:_flush():80] Configure stats pid to 1459
3
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
4
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
5
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_setup.py:_flush():80] Loading settings from environment variables
6
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_173629-7f2wzkw5/logs/debug.log
7
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_173629-7f2wzkw5/logs/debug-internal.log
8
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_init.py:init():840] calling init triggers
9
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
10
+ config: {'model': 'bert-base-multilingual-cased', 'train_file': 'synthetic_data_gen/data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
11
+ 2025-11-22 17:36:29,569 INFO MainThread:1459 [wandb_init.py:init():888] starting backend
12
+ 2025-11-22 17:36:30,292 INFO MainThread:1459 [wandb_init.py:init():891] sending inform_init request
13
+ 2025-11-22 17:36:30,301 INFO MainThread:1459 [wandb_init.py:init():899] backend started and connected
14
+ 2025-11-22 17:36:30,304 INFO MainThread:1459 [wandb_init.py:init():969] updated telemetry
15
+ 2025-11-22 17:36:30,311 INFO MainThread:1459 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
16
+ 2025-11-22 17:36:31,052 INFO MainThread:1459 [wandb_init.py:init():1040] starting run threads in backend
17
+ 2025-11-22 17:36:31,550 INFO MainThread:1459 [wandb_run.py:_console_start():2504] atexit reg
18
+ 2025-11-22 17:36:31,550 INFO MainThread:1459 [wandb_run.py:_redirect():2352] redirect: wrap_raw
19
+ 2025-11-22 17:36:31,550 INFO MainThread:1459 [wandb_run.py:_redirect():2421] Wrapping output streams.
20
+ 2025-11-22 17:36:31,550 INFO MainThread:1459 [wandb_run.py:_redirect():2444] Redirects installed.
21
+ 2025-11-22 17:36:31,556 INFO MainThread:1459 [wandb_init.py:init():1080] run started, returning control to user process
22
+ 2025-11-22 17:36:55,547 INFO MainThread:1459 [wandb_run.py:_config_callback():1385] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'float32', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['BertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'O', 1: 'B-GUJ', 2: 'I-GUJ', 3: 'B-ENG', 4: 'I-ENG'}, 'label2id': {'O': 0, 'B-GUJ': 1, 'I-GUJ': 2, 'B-ENG': 3, 'I-ENG': 4}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'bert-base-multilingual-cased', 'transformers_version': '4.57.1', 'directionality': 'bidi', 'model_type': 'bert', 'pooler_fc_size': 768, 'pooler_num_attention_heads': 12, 'pooler_num_fc_layers': 3, 'pooler_size_per_head': 128, 'pooler_type': 'first_token_transform', 'tf_legacy_loss': False, 'use_bfloat16': False, 'vocab_size': 119547, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_attentions': False, 'output_dir': './models/bert-multilingual-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/bert-multilingual-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'h3110Fr13nd/guj-eng-code-switch-bert-multilingual-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-bert-multilingual-data2', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
23
+ 2025-11-22 17:36:55,553 INFO MainThread:1459 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 177266693 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7aae6e5964e0>>
24
+ 2025-11-22 17:36:55,553 INFO MainThread:1459 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 177266693 None
25
+ 2025-11-22 17:43:27,008 INFO MainThread:1459 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/7f2wzkw5
26
+ 2025-11-22 17:43:27,010 INFO MainThread:1459 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
27
+ 2025-11-22 17:43:27,010 INFO MainThread:1459 [wandb_run.py:_restore():2451] restore
28
+ 2025-11-22 17:43:27,011 INFO MainThread:1459 [wandb_run.py:_restore():2457] restore done
29
+ 2025-11-22 17:43:28,797 INFO MainThread:1459 [wandb_run.py:_footer_sync_info():3853] logging synced files
wandb_logs/run-20251122_173629-7f2wzkw5/run-7f2wzkw5.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1108f7f28b0bc33d05f8cabac53151ed68535bb4a475e0331182f2529307995a
3
+ size 301613
wandb_logs/run-20251122_174431-8mhq2ivv/files/config.yaml ADDED
@@ -0,0 +1,542 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _name_or_path:
2
+ value: ai4bharat/indic-bert
3
+ _wandb:
4
+ value:
5
+ cli_version: 0.23.0
6
+ e:
7
+ 2xsu8y5rc4fgxfx16p7iyzut9btxqkup:
8
+ args:
9
+ - configs/indic_data2.json
10
+ codePath: train.py
11
+ codePathLocal: train.py
12
+ cpu_count: 1
13
+ cpu_count_logical: 2
14
+ cudaVersion: "12.4"
15
+ disk:
16
+ /:
17
+ total: "120942624768"
18
+ used: "49261019136"
19
+ email: vijaysinghkushwaha3737@gmail.com
20
+ executable: /usr/bin/python3
21
+ git:
22
+ commit: c280afc6ba26ad46a6cf9a434272dbf927fafc80
23
+ remote: https://h3110Fr13nd:@github.com/h3110Fr13nd/code-switch-identification-model.git
24
+ gpu: Tesla T4
25
+ gpu_count: 1
26
+ gpu_nvidia:
27
+ - architecture: Turing
28
+ cudaCores: 2560
29
+ memoryTotal: "16106127360"
30
+ name: Tesla T4
31
+ uuid: GPU-1b701237-0e57-cd79-3d08-bb01f3fff16f
32
+ host: 8b09dd3d6919
33
+ memory:
34
+ total: "13605851136"
35
+ os: Linux-6.6.105+-x86_64-with-glibc2.35
36
+ program: /content/code-switch-identification-model/train.py
37
+ python: CPython 3.12.12
38
+ root: /content/code-switch-identification-model
39
+ startedAt: "2025-11-22T17:44:31.444877Z"
40
+ writerId: 2xsu8y5rc4fgxfx16p7iyzut9btxqkup
41
+ m:
42
+ - "1": train/global_step
43
+ "6":
44
+ - 3
45
+ "7": []
46
+ - "2": '*'
47
+ "5": 1
48
+ "6":
49
+ - 1
50
+ "7": []
51
+ python_version: 3.12.12
52
+ t:
53
+ "1":
54
+ - 1
55
+ - 2
56
+ - 3
57
+ - 5
58
+ - 11
59
+ - 12
60
+ - 41
61
+ - 49
62
+ - 51
63
+ - 53
64
+ - 71
65
+ - 98
66
+ - 100
67
+ - 105
68
+ "2":
69
+ - 1
70
+ - 2
71
+ - 3
72
+ - 5
73
+ - 11
74
+ - 12
75
+ - 41
76
+ - 49
77
+ - 51
78
+ - 53
79
+ - 71
80
+ - 98
81
+ - 100
82
+ - 105
83
+ "3":
84
+ - 2
85
+ - 7
86
+ - 13
87
+ - 15
88
+ - 16
89
+ - 19
90
+ - 62
91
+ - 66
92
+ "4": 3.12.12
93
+ "5": 0.23.0
94
+ "6": 4.57.1
95
+ "9":
96
+ "1": transformers_trainer
97
+ "12": 0.23.0
98
+ "13": linux-x86_64
99
+ accelerator_config:
100
+ value:
101
+ dispatch_batches: null
102
+ even_batches: true
103
+ gradient_accumulation_kwargs: null
104
+ non_blocking: false
105
+ split_batches: false
106
+ use_seedable_sampler: true
107
+ adafactor:
108
+ value: false
109
+ adam_beta1:
110
+ value: 0.9
111
+ adam_beta2:
112
+ value: 0.999
113
+ adam_epsilon:
114
+ value: 1e-08
115
+ add_cross_attention:
116
+ value: false
117
+ architectures:
118
+ value: null
119
+ attention_probs_dropout_prob:
120
+ value: 0
121
+ auto_find_batch_size:
122
+ value: false
123
+ average_tokens_across_devices:
124
+ value: true
125
+ bad_words_ids:
126
+ value: null
127
+ batch_eval_metrics:
128
+ value: false
129
+ batch_size:
130
+ value: 16
131
+ begin_suppress_tokens:
132
+ value: null
133
+ bf16:
134
+ value: false
135
+ bf16_full_eval:
136
+ value: false
137
+ bos_token_id:
138
+ value: 2
139
+ chunk_size_feed_forward:
140
+ value: 0
141
+ classifier_dropout_prob:
142
+ value: 0.1
143
+ cross_attention_hidden_size:
144
+ value: null
145
+ data_seed:
146
+ value: null
147
+ dataloader_drop_last:
148
+ value: false
149
+ dataloader_num_workers:
150
+ value: 0
151
+ dataloader_persistent_workers:
152
+ value: false
153
+ dataloader_pin_memory:
154
+ value: true
155
+ dataloader_prefetch_factor:
156
+ value: null
157
+ ddp_backend:
158
+ value: null
159
+ ddp_broadcast_buffers:
160
+ value: null
161
+ ddp_bucket_cap_mb:
162
+ value: null
163
+ ddp_find_unused_parameters:
164
+ value: null
165
+ ddp_timeout:
166
+ value: 1800
167
+ debug:
168
+ value: []
169
+ decoder_start_token_id:
170
+ value: null
171
+ deepspeed:
172
+ value: null
173
+ disable_tqdm:
174
+ value: false
175
+ diversity_penalty:
176
+ value: 0
177
+ do_eval:
178
+ value: true
179
+ do_predict:
180
+ value: false
181
+ do_sample:
182
+ value: false
183
+ do_train:
184
+ value: false
185
+ down_scale_factor:
186
+ value: 1
187
+ dtype:
188
+ value: float32
189
+ early_stopping:
190
+ value: false
191
+ embedding_size:
192
+ value: 128
193
+ encoder_no_repeat_ngram_size:
194
+ value: 0
195
+ eos_token_id:
196
+ value: 3
197
+ epochs:
198
+ value: 3
199
+ eval_accumulation_steps:
200
+ value: null
201
+ eval_delay:
202
+ value: 0
203
+ eval_do_concat_batches:
204
+ value: true
205
+ eval_on_start:
206
+ value: false
207
+ eval_steps:
208
+ value: null
209
+ eval_strategy:
210
+ value: epoch
211
+ eval_use_gather_object:
212
+ value: false
213
+ exponential_decay_length_penalty:
214
+ value: null
215
+ finetuning_task:
216
+ value: null
217
+ forced_bos_token_id:
218
+ value: null
219
+ forced_eos_token_id:
220
+ value: null
221
+ fp16:
222
+ value: false
223
+ fp16_backend:
224
+ value: auto
225
+ fp16_full_eval:
226
+ value: false
227
+ fp16_opt_level:
228
+ value: O1
229
+ fsdp:
230
+ value: []
231
+ fsdp_config:
232
+ value:
233
+ min_num_params: 0
234
+ xla: false
235
+ xla_fsdp_grad_ckpt: false
236
+ xla_fsdp_v2: false
237
+ fsdp_min_num_params:
238
+ value: 0
239
+ fsdp_transformer_layer_cls_to_wrap:
240
+ value: null
241
+ full_determinism:
242
+ value: false
243
+ gap_size:
244
+ value: 0
245
+ gradient_accumulation_steps:
246
+ value: 1
247
+ gradient_checkpointing:
248
+ value: false
249
+ gradient_checkpointing_kwargs:
250
+ value: null
251
+ greater_is_better:
252
+ value: true
253
+ group_by_length:
254
+ value: false
255
+ half_precision_backend:
256
+ value: auto
257
+ hidden_act:
258
+ value: gelu
259
+ hidden_dropout_prob:
260
+ value: 0
261
+ hidden_size:
262
+ value: 768
263
+ hub_always_push:
264
+ value: false
265
+ hub_model_id:
266
+ value: h3110Fr13nd/guj-eng-code-switch-indic-bert-data2
267
+ hub_private_repo:
268
+ value: false
269
+ hub_revision:
270
+ value: null
271
+ hub_strategy:
272
+ value: end
273
+ hub_token:
274
+ value: <HUB_TOKEN>
275
+ id2label:
276
+ value:
277
+ "0": O
278
+ "1": B-GUJ
279
+ "2": I-GUJ
280
+ "3": B-ENG
281
+ "4": I-ENG
282
+ ignore_data_skip:
283
+ value: false
284
+ include_for_metrics:
285
+ value: []
286
+ include_inputs_for_metrics:
287
+ value: false
288
+ include_num_input_tokens_seen:
289
+ value: "no"
290
+ include_tokens_per_second:
291
+ value: false
292
+ initializer_range:
293
+ value: 0.02
294
+ inner_group_num:
295
+ value: 1
296
+ intermediate_size:
297
+ value: 3072
298
+ is_decoder:
299
+ value: false
300
+ is_encoder_decoder:
301
+ value: false
302
+ jit_mode_eval:
303
+ value: false
304
+ label_names:
305
+ value: null
306
+ label_smoothing_factor:
307
+ value: 0
308
+ label2id:
309
+ value:
310
+ B-ENG: 3
311
+ B-GUJ: 1
312
+ I-ENG: 4
313
+ I-GUJ: 2
314
+ O: 0
315
+ layer_norm_eps:
316
+ value: 1e-12
317
+ learning_rate:
318
+ value: 2e-05
319
+ length_column_name:
320
+ value: length
321
+ length_penalty:
322
+ value: 1
323
+ liger_kernel_config:
324
+ value: null
325
+ load_best_model_at_end:
326
+ value: true
327
+ local_rank:
328
+ value: 0
329
+ log_level:
330
+ value: passive
331
+ log_level_replica:
332
+ value: warning
333
+ log_on_each_node:
334
+ value: true
335
+ logging_dir:
336
+ value: ./models/indic-bert-data2/logs
337
+ logging_first_step:
338
+ value: true
339
+ logging_nan_inf_filter:
340
+ value: true
341
+ logging_steps:
342
+ value: 50
343
+ logging_strategy:
344
+ value: steps
345
+ lr_scheduler_type:
346
+ value: linear
347
+ max_grad_norm:
348
+ value: 1
349
+ max_length:
350
+ value: 20
351
+ max_position_embeddings:
352
+ value: 512
353
+ max_steps:
354
+ value: -1
355
+ metric_for_best_model:
356
+ value: f1
357
+ min_length:
358
+ value: 0
359
+ model:
360
+ value: ai4bharat/indic-bert
361
+ model/num_parameters:
362
+ value: 32856837
363
+ model_type:
364
+ value: albert
365
+ mp_parameters:
366
+ value: ""
367
+ neftune_noise_alpha:
368
+ value: null
369
+ net_structure_type:
370
+ value: 0
371
+ no_cuda:
372
+ value: false
373
+ no_repeat_ngram_size:
374
+ value: 0
375
+ num_attention_heads:
376
+ value: 12
377
+ num_beam_groups:
378
+ value: 1
379
+ num_beams:
380
+ value: 1
381
+ num_hidden_groups:
382
+ value: 1
383
+ num_hidden_layers:
384
+ value: 12
385
+ num_memory_blocks:
386
+ value: 0
387
+ num_return_sequences:
388
+ value: 1
389
+ num_train_epochs:
390
+ value: 3
391
+ optim:
392
+ value: adamw_torch_fused
393
+ optim_args:
394
+ value: null
395
+ optim_target_modules:
396
+ value: null
397
+ output_attentions:
398
+ value: false
399
+ output_dir:
400
+ value: ./models/indic-bert-data2
401
+ output_hidden_states:
402
+ value: false
403
+ output_scores:
404
+ value: false
405
+ overwrite_output_dir:
406
+ value: true
407
+ pad_token_id:
408
+ value: 0
409
+ parallelism_config:
410
+ value: null
411
+ past_index:
412
+ value: -1
413
+ per_device_eval_batch_size:
414
+ value: 32
415
+ per_device_train_batch_size:
416
+ value: 16
417
+ per_gpu_eval_batch_size:
418
+ value: null
419
+ per_gpu_train_batch_size:
420
+ value: null
421
+ position_embedding_type:
422
+ value: absolute
423
+ prediction_loss_only:
424
+ value: false
425
+ prefix:
426
+ value: null
427
+ problem_type:
428
+ value: null
429
+ project:
430
+ value: huggingface
431
+ push_to_hub:
432
+ value: true
433
+ push_to_hub_model_id:
434
+ value: guj-eng-code-switch-indic-bert-data2
435
+ push_to_hub_organization:
436
+ value: null
437
+ push_to_hub_token:
438
+ value: <PUSH_TO_HUB_TOKEN>
439
+ ray_scope:
440
+ value: last
441
+ remove_invalid_values:
442
+ value: false
443
+ remove_unused_columns:
444
+ value: true
445
+ repetition_penalty:
446
+ value: 1
447
+ report_to:
448
+ value:
449
+ - tensorboard
450
+ - wandb
451
+ restore_callback_states_from_checkpoint:
452
+ value: false
453
+ resume_from_checkpoint:
454
+ value: null
455
+ return_dict:
456
+ value: true
457
+ return_dict_in_generate:
458
+ value: false
459
+ run_name:
460
+ value: null
461
+ save_on_each_node:
462
+ value: false
463
+ save_only_model:
464
+ value: false
465
+ save_safetensors:
466
+ value: true
467
+ save_steps:
468
+ value: null
469
+ save_strategy:
470
+ value: epoch
471
+ save_total_limit:
472
+ value: 3
473
+ seed:
474
+ value: 42
475
+ sep_token_id:
476
+ value: null
477
+ skip_memory_metrics:
478
+ value: true
479
+ suppress_tokens:
480
+ value: null
481
+ task_specific_params:
482
+ value: null
483
+ temperature:
484
+ value: 1
485
+ tf_legacy_loss:
486
+ value: false
487
+ tf32:
488
+ value: null
489
+ tie_encoder_decoder:
490
+ value: false
491
+ tie_word_embeddings:
492
+ value: true
493
+ tokenizer_class:
494
+ value: null
495
+ top_k:
496
+ value: 50
497
+ top_p:
498
+ value: 1
499
+ torch_compile:
500
+ value: false
501
+ torch_compile_backend:
502
+ value: null
503
+ torch_compile_mode:
504
+ value: null
505
+ torch_empty_cache_steps:
506
+ value: null
507
+ torchdynamo:
508
+ value: null
509
+ torchscript:
510
+ value: false
511
+ tpu_metrics_debug:
512
+ value: false
513
+ tpu_num_cores:
514
+ value: null
515
+ trackio_space_id:
516
+ value: trackio
517
+ train_file:
518
+ value: synthetic_data_gen/data2/train.txt
519
+ transformers_version:
520
+ value: 4.57.1
521
+ type_vocab_size:
522
+ value: 2
523
+ typical_p:
524
+ value: 1
525
+ use_bfloat16:
526
+ value: false
527
+ use_cpu:
528
+ value: false
529
+ use_legacy_prediction_loop:
530
+ value: false
531
+ use_liger_kernel:
532
+ value: false
533
+ use_mps_device:
534
+ value: false
535
+ vocab_size:
536
+ value: 200000
537
+ warmup_ratio:
538
+ value: 0.1
539
+ warmup_steps:
540
+ value: 0
541
+ weight_decay:
542
+ value: 0.01
wandb_logs/run-20251122_174431-8mhq2ivv/files/output.log ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|
3
+ _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|
4
+ _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|
5
+ _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|
6
+ _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|
7
+ Enter your token (input will not be visible):
8
+
9
+ Cannot authenticate through git-credential as no helper is defined on your machine.
10
+ You might have to re-authenticate when pushing to the Hugging Face Hub.
11
+ Run the following command in your terminal in case you want to set the 'store' credential helper as default.
12
+
13
+ git config --global credential.helper store
14
+
15
+ Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.
16
+ Token has not been saved to git credential helper.
17
+ WARNING:huggingface_hub._login:Token has not been saved to git credential helper.
18
+ config.json: 100% 507/507 [00:00<00:00, 2.26MB/s]
19
+ spiece.model: 100% 5.65M/5.65M [00:00<00:00, 8.52MB/s]
20
+ pytorch_model.bin: 100% 135M/135M [00:02<00:00, 52.1MB/s]
21
+ Some weights of AlbertForTokenClassification were not initialized from the model checkpoint at ai4bharat/indic-bert and are newly initialized: ['classifier.bias', 'classifier.weight']
22
+ You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
23
+ 100% 750/750 [02:27<00:00, 5.08it/s]
24
+ {'loss': 1.5877, 'grad_norm': 5.840982437133789, 'learning_rate': 0.0, 'epoch': 0.0}
25
+ {'loss': 1.3469, 'grad_norm': 2.20930814743042, 'learning_rate': 1.3066666666666668e-05, 'epoch': 0.2}
26
+ {'loss': 0.8276, 'grad_norm': 7.204668045043945, 'learning_rate': 1.928888888888889e-05, 'epoch': 0.4}
27
+ {'loss': 0.4284, 'grad_norm': 5.005268096923828, 'learning_rate': 1.780740740740741e-05, 'epoch': 0.6}
28
+ {'loss': 0.2584, 'grad_norm': 2.686133623123169, 'learning_rate': 1.632592592592593e-05, 'epoch': 0.8}
29
+ {'loss': 0.1859, 'grad_norm': 4.183841705322266, 'learning_rate': 1.4844444444444445e-05, 'epoch': 1.0}
30
+ Processing Files (5 / 5) : 100% 152M/152M [00:10<00:00, 14.6MB/s, 15.2MB/s ]
31
+ {'eval_loss': 0.1750897318124771, 'eval_precision': 0.8526955201214882, 'eval_recall': 0.8462697814619442, 'eval_f1': 0.8494704992435704, 'eval_accuracy': 0.9602705644534287, 'eval_runtime': 3.8037, 'eval_samples_per_second': 131.452, 'eval_steps_per_second': 4.206, 'epoch': 1.0}
32
+ {'loss': 0.1546, 'grad_norm': 2.1835110187530518, 'learning_rate': 1.3362962962962964e-05, 'epoch': 1.2}
33
+ {'loss': 0.1246, 'grad_norm': 2.547006368637085, 'learning_rate': 1.1881481481481482e-05, 'epoch': 1.4}
34
+ {'loss': 0.1373, 'grad_norm': 1.817032814025879, 'learning_rate': 1.04e-05, 'epoch': 1.6}
35
+ {'loss': 0.1174, 'grad_norm': 12.349453926086426, 'learning_rate': 8.91851851851852e-06, 'epoch': 1.8}
36
+ {'loss': 0.1184, 'grad_norm': 10.204670906066895, 'learning_rate': 7.437037037037038e-06, 'epoch': 2.0}
37
+ {'eval_loss': 0.136522114276886, 'eval_precision': 0.8784977908689249, 'eval_recall': 0.8990203466465713, 'eval_f1': 0.8886405959031658, 'eval_accuracy': 0.9638469911366817, 'eval_runtime': 3.8696, 'eval_samples_per_second': 129.212, 'eval_steps_per_second': 4.135, 'epoch': 2.0}
38
+ {'loss': 0.1013, 'grad_norm': 1.3042551279067993, 'learning_rate': 5.955555555555555e-06, 'epoch': 2.2}
39
+ {'loss': 0.0979, 'grad_norm': 2.062248945236206, 'learning_rate': 4.4740740740740746e-06, 'epoch': 2.4}
40
+ {'loss': 0.0818, 'grad_norm': 0.25782376527786255, 'learning_rate': 2.992592592592593e-06, 'epoch': 2.6}
41
+ {'loss': 0.067, 'grad_norm': 1.4104307889938354, 'learning_rate': 1.5111111111111112e-06, 'epoch': 2.8}
42
+ {'loss': 0.0726, 'grad_norm': 0.6216073036193848, 'learning_rate': 2.9629629629629632e-08, 'epoch': 3.0}
43
+ {'eval_loss': 0.10922063887119293, 'eval_precision': 0.8988929889298893, 'eval_recall': 0.9178598342125094, 'eval_f1': 0.9082774049217002, 'eval_accuracy': 0.9728658062509719, 'eval_runtime': 3.7874, 'eval_samples_per_second': 132.015, 'eval_steps_per_second': 4.224, 'epoch': 3.0}
44
+ {'train_runtime': 147.6466, 'train_samples_per_second': 81.275, 'train_steps_per_second': 5.08, 'train_loss': 0.27498963912328084, 'epoch': 3.0}
45
+ New Data Upload : 100% 131M/131M [00:10<00:00, 12.6MB/s, 13.1MB/s ]
46
+ ...t-data2/training_args.bin: 100% 5.91k/5.91k [00:09<?, ?B/s]
47
+ ...bert-data2/tokenizer.json: 100% 15.3M/15.3M [00:08<?, ?B/s]
48
+ ...t-data2/model.safetensors: 100% 131M/131M [00:08<00:00, 15.6MB/s]
49
+ ...c-bert-data2/spiece.model: 100% 5.65M/5.65M [00:07<?, ?B/s]
50
+ ...33799.8b09dd3d6919.3693.0: 100% 10.5k/10.5k [00:07<00:00, 1.49kB/s]
51
+ Processing Files (5 / 5) : 100% 152M/152M [00:01<00:00, 108MB/s, 95.6MB/s ]
52
+ New Data Upload : | | 0.00B / 0.00B, 0.00B/s
53
+ ...t-data2/training_args.bin: 100% 5.91k/5.91k [00:01<?, ?B/s]
54
+ ...33799.8b09dd3d6919.3693.0: 100% 10.5k/10.5k [00:01<?, ?B/s]
55
+ ...c-bert-data2/spiece.model: 100% 5.65M/5.65M [00:01<?, ?B/s]
56
+ ...bert-data2/tokenizer.json: 100% 15.3M/15.3M [00:01<?, ?B/s]
57
+ ...t-data2/model.safetensors: 100% 131M/131M [00:01<00:00, 95.8MB/s]
58
+ No files have been modified since last commit. Skipping to prevent empty commit.
59
+ WARNING:huggingface_hub.hf_api:No files have been modified since last commit. Skipping to prevent empty commit.
60
+ ***** train metrics *****
61
+ epoch = 3.0
62
+ total_flos = 31119GF
63
+ train_loss = 0.275
64
+ train_runtime = 0:02:27.64
65
+ train_samples_per_second = 81.275
66
+ train_steps_per_second = 5.08
67
+ 100% 16/16 [00:03<00:00, 4.42it/s]
68
+ ***** eval metrics *****
69
+ epoch = 3.0
70
+ eval_accuracy = 0.9729
71
+ eval_f1 = 0.9083
72
+ eval_loss = 0.1092
73
+ eval_precision = 0.8989
74
+ eval_recall = 0.9179
75
+ eval_runtime = 0:00:03.78
76
+ eval_samples_per_second = 132.009
77
+ eval_steps_per_second = 4.224
78
+ 94% 15/16 [00:01<00:00, 7.53it/s]early stopping required metric_for_best_model, but did not find eval_f1 so early stopping is disabled
79
+ 100% 16/16 [00:03<00:00, 4.63it/s]
80
+ ***** test metrics *****
81
+ epoch = 3.0
82
+ test_accuracy = 0.9832
83
+ test_f1 = 0.9265
84
+ test_loss = 0.0772
85
+ test_precision = 0.9255
86
+ test_recall = 0.9275
87
+ test_runtime = 0:00:03.63
88
+ test_samples_per_second = 137.699
89
+ test_steps_per_second = 4.406
wandb_logs/run-20251122_174431-8mhq2ivv/files/requirements.txt ADDED
@@ -0,0 +1,698 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ setuptools==75.2.0
2
+ pip==24.1.2
3
+ requirements-parser==0.9.0
4
+ types-setuptools==80.9.0.20250822
5
+ ipykernel==7.1.0
6
+ tensorboard==2.20.0
7
+ numpy==2.3.5
8
+ pyarrow==22.0.0
9
+ matplotlib==3.10.7
10
+ widgetsnbextension==4.0.15
11
+ seqeval==1.2.2
12
+ ipywidgets==8.1.8
13
+ datasets==4.4.1
14
+ pandas==2.3.3
15
+ comm==0.2.3
16
+ google-genai==1.50.1
17
+ scikit-learn==1.7.2
18
+ evaluate==0.4.6
19
+ jedi==0.19.2
20
+ jupyter_client==8.6.3
21
+ google-colab==1.0.0
22
+ httpcore==1.0.9
23
+ colorlover==0.3.0
24
+ pyOpenSSL==24.2.1
25
+ PySocks==1.7.1
26
+ fsspec==2025.3.0
27
+ google-ai-generativelanguage==0.6.15
28
+ dlib==19.24.6
29
+ fastdownload==0.0.7
30
+ jaxlib==0.7.2
31
+ python-multipart==0.0.20
32
+ nltk==3.9.1
33
+ chardet==5.2.0
34
+ pyparsing==3.2.5
35
+ sentry-sdk==2.45.0
36
+ audioread==3.1.0
37
+ langchain-core==0.3.80
38
+ jaraco.classes==3.4.0
39
+ cymem==2.0.13
40
+ vega-datasets==0.9.0
41
+ docstring_parser==0.17.0
42
+ nest-asyncio==1.6.0
43
+ mlxtend==0.23.4
44
+ xyzservices==2025.10.0
45
+ more-itertools==10.8.0
46
+ torchao==0.10.0
47
+ numba==0.60.0
48
+ panel==1.8.3
49
+ docutils==0.21.2
50
+ holoviews==1.22.0
51
+ attrs==25.4.0
52
+ db-dtypes==1.4.4
53
+ tabulate==0.9.0
54
+ pydotplus==2.0.2
55
+ soundfile==0.13.1
56
+ sklearn-pandas==2.2.0
57
+ multitasking==0.0.12
58
+ glob2==0.7
59
+ nvidia-cusolver-cu12==11.7.1.2
60
+ google-adk==1.17.0
61
+ alabaster==1.0.0
62
+ mdit-py-plugins==0.5.0
63
+ intel-cmplr-lib-ur==2025.3.1
64
+ nvidia-cufft-cu12==11.3.0.4
65
+ google-cloud-bigquery-connection==1.19.0
66
+ polars==1.31.0
67
+ openai==1.109.1
68
+ google-cloud-spanner==3.59.0
69
+ patsy==1.0.2
70
+ pytest==8.4.2
71
+ pycparser==2.23
72
+ curl_cffi==0.13.0
73
+ linkify-it-py==2.0.3
74
+ imutils==0.5.4
75
+ Markdown==3.10
76
+ pandas-stubs==2.2.2.240909
77
+ pooch==1.8.2
78
+ pandas-gbq==0.30.0
79
+ google-cloud-dataproc==5.23.0
80
+ google-cloud-language==2.18.0
81
+ jupyter_kernel_gateway==2.5.2
82
+ google-resumable-media==2.8.0
83
+ nvidia-cuda-runtime-cu12==12.6.77
84
+ dask-cudf-cu12==25.10.0
85
+ websocket-client==1.9.0
86
+ distributed-ucxx-cu12==0.46.0
87
+ altair==5.5.0
88
+ idna==3.11
89
+ wandb==0.23.0
90
+ moviepy==1.0.3
91
+ click==8.3.1
92
+ oauth2client==4.1.3
93
+ GDAL==3.8.4
94
+ mcp==1.21.2
95
+ pyzmq==26.2.1
96
+ langsmith==0.4.43
97
+ sqlparse==0.5.3
98
+ betterproto==2.0.0b6
99
+ parso==0.8.5
100
+ imbalanced-learn==0.14.0
101
+ tbb==2022.3.0
102
+ dm-tree==0.1.9
103
+ cuda-python==12.9.4
104
+ pygit2==1.19.0
105
+ proglog==0.1.12
106
+ fastjsonschema==2.21.2
107
+ tornado==6.5.1
108
+ matplotlib-venn==1.1.2
109
+ Authlib==1.6.5
110
+ cryptography==43.0.3
111
+ snowballstemmer==3.0.1
112
+ networkx==3.5
113
+ nvidia-cublas-cu12==12.6.4.1
114
+ wcwidth==0.2.14
115
+ dopamine_rl==4.1.2
116
+ blobfile==3.1.0
117
+ simple-parsing==0.1.7
118
+ pylibcugraph-cu12==25.10.1
119
+ sentence-transformers==5.1.2
120
+ jsonpatch==1.33
121
+ webencodings==0.5.1
122
+ zict==3.0.0
123
+ google-cloud-bigquery-storage==2.34.0
124
+ sphinxcontrib-serializinghtml==2.0.0
125
+ uc-micro-py==1.0.3
126
+ rfc3987-syntax==1.1.0
127
+ itsdangerous==2.2.0
128
+ peft==0.18.0
129
+ gspread-dataframe==4.0.0
130
+ pydot==3.0.4
131
+ pydantic_core==2.33.2
132
+ oauthlib==3.3.1
133
+ google-cloud-bigquery==3.38.0
134
+ geopy==2.4.1
135
+ rmm-cu12==25.10.0
136
+ distributed==2025.9.1
137
+ pandocfilters==1.5.1
138
+ llvmlite==0.43.0
139
+ torchaudio==2.9.0+cu126
140
+ hdbscan==0.8.40
141
+ safetensors==0.7.0
142
+ et_xmlfile==2.0.0
143
+ numexpr==2.14.1
144
+ scs==3.2.9
145
+ importlib_resources==6.5.2
146
+ pyogrio==0.11.1
147
+ rapids-logger==0.1.19
148
+ google==2.0.3
149
+ blinker==1.9.0
150
+ colour==0.1.5
151
+ lightgbm==4.6.0
152
+ pylibraft-cu12==25.10.0
153
+ autograd==1.8.0
154
+ duckdb==1.3.2
155
+ typing_extensions==4.15.0
156
+ protobuf==5.29.5
157
+ argon2-cffi==25.1.0
158
+ Bottleneck==1.4.2
159
+ libucxx-cu12==0.46.0
160
+ libcugraph-cu12==25.10.1
161
+ huggingface-hub==0.36.0
162
+ fastapi==0.121.3
163
+ mistune==3.1.4
164
+ pyspark==3.5.1
165
+ ibis-framework==9.5.0
166
+ tqdm==4.67.1
167
+ seaborn==0.13.2
168
+ mdurl==0.1.2
169
+ stumpy==1.13.0
170
+ python-dotenv==1.2.1
171
+ psygnal==0.15.0
172
+ music21==9.3.0
173
+ Farama-Notifications==0.0.4
174
+ jsonschema-specifications==2025.9.1
175
+ xxhash==3.6.0
176
+ confection==0.1.5
177
+ treelite==4.4.1
178
+ httpimport==1.4.1
179
+ libpysal==4.13.0
180
+ cramjam==2.11.0
181
+ google-cloud-functions==1.21.0
182
+ grpcio-status==1.71.2
183
+ torchsummary==1.5.1
184
+ nvidia-nvshmem-cu12==3.3.20
185
+ libucx-cu12==1.19.0
186
+ geopandas==1.1.1
187
+ toml==0.10.2
188
+ shapely==2.1.2
189
+ html5lib==1.1
190
+ antlr4-python3-runtime==4.9.3
191
+ clarabel==0.11.1
192
+ uvicorn==0.38.0
193
+ toolz==0.12.1
194
+ cloudpathlib==0.23.0
195
+ cupy-cuda12x==13.6.0
196
+ fastai==2.8.5
197
+ peewee==3.18.3
198
+ GitPython==3.1.45
199
+ aiohappyeyeballs==2.6.1
200
+ murmurhash==1.0.15
201
+ jax-cuda12-plugin==0.7.2
202
+ pyperclip==1.11.0
203
+ promise==2.3
204
+ jupyter_server==2.14.0
205
+ webcolors==25.10.0
206
+ imagesize==1.4.1
207
+ prettytable==3.17.0
208
+ alembic==1.17.2
209
+ progressbar2==4.5.0
210
+ requests==2.32.4
211
+ nvidia-ml-py==13.580.82
212
+ humanize==4.14.0
213
+ umap-learn==0.5.9.post2
214
+ h5netcdf==1.7.3
215
+ PyGObject==3.42.0
216
+ google-cloud-aiplatform==1.128.0
217
+ flatbuffers==25.9.23
218
+ optax==0.2.6
219
+ nvidia-cuda-cupti-cu12==12.6.80
220
+ nx-cugraph-cu12==25.10.0
221
+ lark==1.3.1
222
+ tenacity==8.5.0
223
+ entrypoints==0.4
224
+ prompt_toolkit==3.0.52
225
+ fonttools==4.60.1
226
+ ffmpy==1.0.0
227
+ google-cloud-core==2.5.0
228
+ matplotlib-inline==0.2.1
229
+ sphinxcontrib-jsmath==1.0.1
230
+ ply==3.11
231
+ tweepy==4.16.0
232
+ en_core_web_sm==3.8.0
233
+ google-crc32c==1.7.1
234
+ libcudf-cu12==25.10.0
235
+ ipytree==0.2.2
236
+ ImageIO==2.37.2
237
+ rfc3339-validator==0.1.4
238
+ keras==3.10.0
239
+ opt_einsum==3.4.0
240
+ jupyter_server_terminals==0.5.3
241
+ rpds-py==0.29.0
242
+ threadpoolctl==3.6.0
243
+ urllib3==2.5.0
244
+ kagglehub==0.3.13
245
+ Flask==3.1.2
246
+ easydict==1.13
247
+ grpcio==1.76.0
248
+ ratelim==0.1.6
249
+ logical-unification==0.4.7
250
+ omegaconf==2.3.0
251
+ roman-numerals-py==3.1.0
252
+ dataproc-spark-connect==0.8.3
253
+ langchain-text-splitters==0.3.11
254
+ tinycss2==1.4.0
255
+ python-json-logger==4.0.0
256
+ scikit-image==0.25.2
257
+ highspy==1.12.0
258
+ tf-slim==1.1.0
259
+ torchtune==0.6.1
260
+ jupyter-console==6.6.3
261
+ spanner-graph-notebook==1.1.8
262
+ dill==0.3.8
263
+ tensorboard-data-server==0.7.2
264
+ slicer==0.0.8
265
+ keyring==25.7.0
266
+ arviz==0.22.0
267
+ sympy==1.13.3
268
+ google-cloud-resource-manager==1.15.0
269
+ traittypes==0.2.3
270
+ typer-slim==0.20.0
271
+ annotated-doc==0.0.4
272
+ hf-xet==1.2.0
273
+ dask-cuda==25.10.0
274
+ pymc==5.26.1
275
+ pynndescent==0.5.13
276
+ stanio==0.5.1
277
+ treescope==0.1.10
278
+ optree==0.18.0
279
+ propcache==0.4.1
280
+ rich==13.9.4
281
+ gcsfs==2025.3.0
282
+ torch==2.9.0+cu126
283
+ MarkupSafe==3.0.3
284
+ tzlocal==5.3.1
285
+ google-cloud-secret-manager==2.25.0
286
+ atpublic==5.1
287
+ gitdb==4.0.12
288
+ ruff==0.14.5
289
+ opentelemetry-exporter-gcp-monitoring==1.11.0a0
290
+ grpc-interceptor==0.15.4
291
+ opentelemetry-exporter-gcp-logging==1.11.0a0
292
+ fqdn==1.5.1
293
+ soxr==1.0.0
294
+ hf_transfer==0.1.9
295
+ pyasn1==0.6.1
296
+ geemap==0.35.3
297
+ regex==2024.11.6
298
+ ipython-sql==0.5.0
299
+ pyviz_comms==3.0.6
300
+ pydub==0.25.1
301
+ geographiclib==2.1
302
+ Jinja2==3.1.6
303
+ ipython-genutils==0.2.0
304
+ multiprocess==0.70.16
305
+ h11==0.16.0
306
+ tables==3.10.2
307
+ tensorflow-text==2.19.0
308
+ bokeh==3.7.3
309
+ opentelemetry-resourcedetector-gcp==1.11.0a0
310
+ beautifulsoup4==4.13.5
311
+ filelock==3.20.0
312
+ catalogue==2.0.10
313
+ fasttransform==0.0.2
314
+ typeguard==4.4.4
315
+ openpyxl==3.1.5
316
+ tokenizers==0.22.1
317
+ plotly==5.24.1
318
+ ucxx-cu12==0.46.0
319
+ branca==0.8.2
320
+ overrides==7.7.0
321
+ cuda-core==0.3.2
322
+ tensorflow-probability==0.25.0
323
+ xarray-einstats==0.9.1
324
+ tf_keras==2.19.0
325
+ referencing==0.37.0
326
+ argon2-cffi-bindings==25.1.0
327
+ librmm-cu12==25.10.0
328
+ nvidia-cusparse-cu12==12.5.4.2
329
+ google-cloud-discoveryengine==0.13.12
330
+ xgboost==3.1.1
331
+ diffusers==0.35.2
332
+ timm==1.0.22
333
+ PyDrive2==1.21.3
334
+ tblib==3.2.2
335
+ scooby==0.11.0
336
+ opencv-python-headless==4.12.0.88
337
+ wheel==0.45.1
338
+ firebase-admin==6.9.0
339
+ shap==0.50.0
340
+ jsonpointer==3.0.0
341
+ python-louvain==0.16
342
+ charset-normalizer==3.4.4
343
+ sqlglot==25.20.2
344
+ jsonschema==4.25.1
345
+ jieba==0.42.1
346
+ importlib_metadata==8.7.0
347
+ nvidia-cuda-nvrtc-cu12==12.6.77
348
+ editdistance==0.8.1
349
+ jax==0.7.2
350
+ google-api-core==2.28.1
351
+ shellingham==1.5.4
352
+ portpicker==1.5.2
353
+ cudf-cu12==25.10.0
354
+ gspread==6.2.1
355
+ pylibcudf-cu12==25.10.0
356
+ python-slugify==8.0.4
357
+ anywidget==0.9.21
358
+ distro==1.9.0
359
+ stringzilla==4.2.3
360
+ libcuml-cu12==25.10.0
361
+ graphviz==0.21
362
+ ipython==7.34.0
363
+ hyperopt==0.2.7
364
+ sniffio==1.3.1
365
+ python-utils==3.9.1
366
+ bigframes==2.29.1
367
+ folium==0.20.0
368
+ google-cloud-bigtable==2.34.0
369
+ text-unidecode==1.3
370
+ pydantic-settings==2.12.0
371
+ annotated-types==0.7.0
372
+ locket==1.0.0
373
+ pyproj==3.7.2
374
+ orbax-checkpoint==0.11.28
375
+ PyJWT==2.10.1
376
+ natsort==8.4.0
377
+ astropy-iers-data==0.2025.11.10.0.38.31
378
+ gym-notices==0.1.0
379
+ debugpy==1.8.15
380
+ weasel==0.4.3
381
+ PyOpenGL==3.1.10
382
+ pydata-google-auth==1.9.1
383
+ semantic-version==2.10.0
384
+ google-cloud-firestore==2.21.0
385
+ statsmodels==0.14.5
386
+ pycocotools==2.0.10
387
+ greenlet==3.2.4
388
+ Werkzeug==3.1.3
389
+ preshed==3.0.12
390
+ gymnasium==1.2.2
391
+ prometheus_client==0.23.1
392
+ triton==3.5.0
393
+ frozendict==2.4.7
394
+ multipledispatch==1.0.0
395
+ srsly==2.5.2
396
+ google-auth-httplib2==0.2.1
397
+ zstandard==0.25.0
398
+ uri-template==1.3.0
399
+ gradio==5.49.1
400
+ websockets==15.0.1
401
+ bigquery-magics==0.10.3
402
+ nvidia-cuda-nvcc-cu12==12.5.82
403
+ etils==1.13.0
404
+ cufflinks==0.17.3
405
+ simsimd==6.5.3
406
+ frozenlist==1.8.0
407
+ transformers==4.57.1
408
+ ale-py==0.11.2
409
+ orjson==3.11.4
410
+ jiter==0.12.0
411
+ safehttpx==0.1.7
412
+ google-auth==2.38.0
413
+ inflect==7.5.0
414
+ decorator==4.4.2
415
+ types-pytz==2025.2.0.20251108
416
+ cyipopt==1.5.0
417
+ imageio-ffmpeg==0.6.0
418
+ pyshp==3.0.2.post1
419
+ grpc-google-iam-v1==0.14.3
420
+ immutabledict==4.2.2
421
+ ipyparallel==8.8.0
422
+ beartype==0.22.5
423
+ keras-nlp==0.21.1
424
+ tensorflow-hub==0.16.1
425
+ yfinance==0.2.66
426
+ cuda-toolkit==12.9.1
427
+ googleapis-common-protos==1.72.0
428
+ google-generativeai==0.8.5
429
+ aiofiles==24.1.0
430
+ joblib==1.5.2
431
+ ndindex==1.10.1
432
+ nbformat==5.10.4
433
+ pygame==2.6.1
434
+ opentelemetry-proto==1.37.0
435
+ cachetools==5.5.2
436
+ sphinxcontrib-qthelp==2.0.0
437
+ albumentations==2.0.8
438
+ libraft-cu12==25.10.0
439
+ absl-py==1.4.0
440
+ simplejson==3.20.2
441
+ jupytext==1.17.3
442
+ raft-dask-cu12==25.10.0
443
+ pyomo==6.9.5
444
+ msgpack==1.1.2
445
+ tensorflow==2.19.0
446
+ dask==2025.9.1
447
+ aiohttp==3.13.2
448
+ future==1.0.0
449
+ bleach==6.3.0
450
+ cmdstanpy==1.3.0
451
+ wurlitzer==3.1.1
452
+ libkvikio-cu12==25.10.0
453
+ google-cloud-audit-log==0.4.0
454
+ packaging==25.0
455
+ defusedxml==0.7.1
456
+ google-auth-oauthlib==1.2.3
457
+ textblob==0.19.0
458
+ pexpect==4.9.0
459
+ Mako==1.3.10
460
+ cmake==3.31.6
461
+ eerepr==0.1.2
462
+ namex==0.1.0
463
+ sse-starlette==3.0.3
464
+ grpclib==0.4.8
465
+ jaraco.context==6.0.1
466
+ nbclient==0.10.2
467
+ scipy==1.16.3
468
+ miniKanren==1.0.5
469
+ nvidia-curand-cu12==10.3.7.77
470
+ sphinxcontrib-applehelp==2.0.0
471
+ python-dateutil==2.9.0.post0
472
+ librosa==0.11.0
473
+ ptyprocess==0.7.0
474
+ opentelemetry-api==1.37.0
475
+ nvtx==0.2.13
476
+ nvidia-cufile-cu12==1.11.1.6
477
+ plum-dispatch==2.6.0
478
+ kiwisolver==1.4.9
479
+ ipyleaflet==0.20.0
480
+ jaraco.functools==4.3.0
481
+ terminado==0.18.1
482
+ tensorflow_decision_forests==1.12.0
483
+ Send2Trash==1.8.3
484
+ flax==0.10.7
485
+ PyWavelets==1.9.0
486
+ brotli==1.2.0
487
+ mpmath==1.3.0
488
+ earthengine-api==1.5.24
489
+ isoduration==20.11.0
490
+ pytz==2025.2
491
+ tiktoken==0.12.0
492
+ traitlets==5.7.1
493
+ typer==0.20.0
494
+ plotnine==0.14.5
495
+ sphinxcontrib-devhelp==2.0.0
496
+ spacy==3.8.11
497
+ gym==0.25.2
498
+ google-cloud-datastore==2.21.0
499
+ torchdata==0.11.0
500
+ bqplot==0.12.45
501
+ missingno==0.5.2
502
+ nvidia-cudnn-cu12==9.10.2.21
503
+ param==2.3.0
504
+ tensorstore==0.1.79
505
+ ipyfilechooser==0.6.0
506
+ rfc3986-validator==0.1.1
507
+ nibabel==5.3.2
508
+ starlette==0.50.0
509
+ psutil==5.9.5
510
+ lazy_loader==0.4
511
+ smart_open==7.5.0
512
+ jupyter_core==5.9.1
513
+ pycairo==1.29.0
514
+ pytensor==2.35.1
515
+ hpack==4.1.0
516
+ smmap==5.0.2
517
+ httplib2==0.31.0
518
+ h2==4.3.0
519
+ nvidia-nccl-cu12==2.27.5
520
+ googledrivedownloader==1.1.0
521
+ SQLAlchemy==2.0.44
522
+ yellowbrick==1.5
523
+ cloudpickle==3.1.2
524
+ typing-inspection==0.4.2
525
+ cuml-cu12==25.10.0
526
+ tensorflow-metadata==1.17.2
527
+ hyperframe==6.1.0
528
+ numba-cuda==0.19.1
529
+ rpy2==3.5.17
530
+ cuda-bindings==12.9.4
531
+ langchain==0.3.27
532
+ array_record==0.8.3
533
+ google-cloud-appengine-logging==1.7.0
534
+ requests-oauthlib==2.0.0
535
+ lxml==5.4.0
536
+ rsa==4.9.1
537
+ thinc==8.3.10
538
+ tomlkit==0.13.3
539
+ blis==1.3.3
540
+ opentelemetry-sdk==1.37.0
541
+ kaggle==1.7.4.5
542
+ tcmlib==1.4.1
543
+ holidays==0.85
544
+ multidict==6.7.0
545
+ accelerate==1.11.0
546
+ pyerfa==2.0.1.5
547
+ babel==2.17.0
548
+ google-api-python-client==2.187.0
549
+ cffi==2.0.0
550
+ soupsieve==2.8
551
+ opencv-python==4.12.0.88
552
+ rapids-dask-dependency==25.10.0
553
+ chex==0.1.90
554
+ google-cloud-translate==3.23.0
555
+ python-snappy==0.7.3
556
+ xarray==2025.11.0
557
+ pillow==11.3.0
558
+ uritemplate==4.2.0
559
+ Cython==3.0.12
560
+ tensorflow-datasets==4.9.9
561
+ mkl==2025.2.0
562
+ cvxpy==1.6.7
563
+ spacy-loggers==1.0.5
564
+ keyrings.google-artifactregistry-auth==1.1.2
565
+ spacy-legacy==3.0.12
566
+ fastrlock==0.8.3
567
+ aiosignal==1.4.0
568
+ osqp==1.0.5
569
+ astunparse==1.6.3
570
+ py-cpuinfo==9.0.0
571
+ nbclassic==1.3.3
572
+ pycryptodomex==3.23.0
573
+ anyio==4.11.0
574
+ ydf==0.13.0
575
+ parsy==2.2
576
+ einops==0.8.1
577
+ iniconfig==2.3.0
578
+ cycler==0.12.1
579
+ h5py==3.15.1
580
+ libclang==18.1.1
581
+ gdown==5.2.0
582
+ wasabi==1.1.3
583
+ httpx==0.28.1
584
+ termcolor==3.2.0
585
+ umf==1.0.2
586
+ mizani==0.13.5
587
+ astropy==7.1.1
588
+ opentelemetry-exporter-gcp-trace==1.11.0
589
+ pandas-datareader==0.10.0
590
+ nvidia-nvjitlink-cu12==12.6.85
591
+ pickleshare==0.7.5
592
+ community==1.0.0b1
593
+ prophet==1.1.7
594
+ jupyterlab_pygments==0.3.0
595
+ requests-toolbelt==1.0.0
596
+ gradio_client==1.13.3
597
+ pydantic==2.11.10
598
+ google-cloud-logging==3.12.1
599
+ google-cloud-storage==2.19.0
600
+ intel-openmp==2025.3.1
601
+ tifffile==2025.10.16
602
+ colorcet==3.1.0
603
+ google-cloud-speech==2.34.0
604
+ notebook_shim==0.2.4
605
+ xlrd==2.0.2
606
+ httpx-sse==0.4.3
607
+ backcall==0.2.0
608
+ blosc2==3.11.1
609
+ sortedcontainers==2.4.0
610
+ opentelemetry-exporter-otlp-proto-common==1.37.0
611
+ sentencepiece==0.2.1
612
+ six==1.17.0
613
+ google-pasta==0.2.0
614
+ sphinxcontrib-htmlhelp==2.1.0
615
+ zipp==3.23.0
616
+ jupyter-leaflet==0.20.0
617
+ jeepney==0.9.0
618
+ cons==0.4.7
619
+ markdown-it-py==4.0.0
620
+ wordcloud==1.9.4
621
+ opencv-contrib-python==4.12.0.88
622
+ opentelemetry-exporter-otlp-proto-http==1.37.0
623
+ absolufy-imports==0.3.1
624
+ psycopg2==2.9.11
625
+ groovy==0.1.2
626
+ CacheControl==0.14.4
627
+ arrow==1.4.0
628
+ ipyevents==2.0.4
629
+ tzdata==2025.2
630
+ nvidia-nvtx-cu12==12.6.77
631
+ Sphinx==8.2.3
632
+ tsfresh==0.21.1
633
+ jupyter-events==0.12.0
634
+ partd==1.4.2
635
+ platformdirs==4.5.0
636
+ SecretStorage==3.4.1
637
+ narwhals==2.12.0
638
+ sqlalchemy-spanner==1.17.1
639
+ watchdog==6.0.0
640
+ nbconvert==7.16.6
641
+ google-cloud-trace==1.17.0
642
+ cuda-pathfinder==1.3.2
643
+ proto-plus==1.26.1
644
+ notebook==6.5.7
645
+ fastcore==1.8.16
646
+ pluggy==1.6.0
647
+ etuples==0.3.10
648
+ gast==0.6.0
649
+ PyYAML==6.0.3
650
+ opentelemetry-semantic-conventions==0.58b0
651
+ ml_dtypes==0.5.4
652
+ google-cloud-monitoring==2.28.0
653
+ pyasn1_modules==0.4.2
654
+ cvxopt==1.3.2
655
+ contourpy==1.3.3
656
+ gin-config==0.5.0
657
+ certifi==2025.11.12
658
+ jsonpickle==4.1.1
659
+ wrapt==2.0.1
660
+ keras-hub==0.21.1
661
+ torchvision==0.24.0+cu126
662
+ yarl==1.22.0
663
+ jupyterlab_widgets==3.0.16
664
+ py4j==0.10.9.7
665
+ Pygments==2.19.2
666
+ python-box==7.3.2
667
+ albucore==0.0.24
668
+ nvidia-cuda-cccl-cu12==12.9.27
669
+ jax-cuda12-pjrt==0.7.2
670
+ fastprogress==1.0.3
671
+ nvidia-cusparselt-cu12==0.7.1
672
+ geocoder==1.38.1
673
+ cudf-polars-cu12==25.10.0
674
+ python-apt==0.0.0
675
+ httplib2==0.20.2
676
+ more-itertools==8.10.0
677
+ oauthlib==3.2.0
678
+ pyparsing==2.4.7
679
+ PyGObject==3.42.1
680
+ lazr.restfulclient==0.14.4
681
+ lazr.uri==1.0.6
682
+ PyJWT==2.3.0
683
+ blinker==1.4
684
+ python-apt==2.4.0+ubuntu4
685
+ launchpadlib==1.10.16
686
+ six==1.16.0
687
+ zipp==1.0.0
688
+ importlib-metadata==4.6.4
689
+ dbus-python==1.2.18
690
+ wadllib==1.3.6
691
+ cryptography==3.4.8
692
+ distro==1.7.0
693
+ keyring==23.5.0
694
+ SecretStorage==3.3.1
695
+ jeepney==0.7.1
696
+ Markdown==3.3.6
697
+ Mako==1.1.3
698
+ MarkupSafe==2.0.1
wandb_logs/run-20251122_174431-8mhq2ivv/files/wandb-metadata.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.6.105+-x86_64-with-glibc2.35",
3
+ "python": "CPython 3.12.12",
4
+ "startedAt": "2025-11-22T17:44:31.444877Z",
5
+ "args": [
6
+ "configs/indic_data2.json"
7
+ ],
8
+ "program": "/content/code-switch-identification-model/train.py",
9
+ "codePath": "train.py",
10
+ "codePathLocal": "train.py",
11
+ "git": {
12
+ "remote": "https://h3110Fr13nd:@github.com/h3110Fr13nd/code-switch-identification-model.git",
13
+ "commit": "c280afc6ba26ad46a6cf9a434272dbf927fafc80"
14
+ },
15
+ "email": "vijaysinghkushwaha3737@gmail.com",
16
+ "root": "/content/code-switch-identification-model",
17
+ "host": "8b09dd3d6919",
18
+ "executable": "/usr/bin/python3",
19
+ "cpu_count": 1,
20
+ "cpu_count_logical": 2,
21
+ "gpu": "Tesla T4",
22
+ "gpu_count": 1,
23
+ "disk": {
24
+ "/": {
25
+ "total": "120942624768",
26
+ "used": "49261019136"
27
+ }
28
+ },
29
+ "memory": {
30
+ "total": "13605851136"
31
+ },
32
+ "gpu_nvidia": [
33
+ {
34
+ "name": "Tesla T4",
35
+ "memoryTotal": "16106127360",
36
+ "cudaCores": 2560,
37
+ "architecture": "Turing",
38
+ "uuid": "GPU-1b701237-0e57-cd79-3d08-bb01f3fff16f"
39
+ }
40
+ ],
41
+ "cudaVersion": "12.4",
42
+ "writerId": "2xsu8y5rc4fgxfx16p7iyzut9btxqkup"
43
+ }
wandb_logs/run-20251122_174431-8mhq2ivv/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/learning_rate":2.9629629629629632e-08,"test/f1":0.926498303807011,"train/grad_norm":0.6216073036193848,"train/global_step":750,"eval/precision":0.8988929889298893,"eval/accuracy":0.9728658062509719,"test/precision":0.9254518072289156,"total_flos":3.341385216864e+13,"test/recall":0.9275471698113208,"train_runtime":147.6466,"train/epoch":3,"test/runtime":3.6311,"train_steps_per_second":5.08,"eval/samples_per_second":132.009,"train/loss":0.0726,"_step":21,"test/loss":0.07724323868751526,"train_samples_per_second":81.275,"eval/runtime":3.7876,"_wandb":{"runtime":501},"_timestamp":1.7638339736842327e+09,"eval/recall":0.9178598342125094,"eval/f1":0.9082774049217002,"test/steps_per_second":4.406,"_runtime":501,"eval/steps_per_second":4.224,"test/samples_per_second":137.699,"train_loss":0.27498963912328084,"eval/loss":0.10922063887119293,"test/accuracy":0.9831719320527068}
wandb_logs/run-20251122_174431-8mhq2ivv/logs/debug-core.log ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-11-22T17:44:31.584078489Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpmz1jf1xh/port-3693.txt","pid":3693,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2025-11-22T17:44:31.585009351Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-3693-3790-1420714249/socket","Net":"unix"}}
3
+ {"time":"2025-11-22T17:44:31.585164344Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":3693}
4
+ {"time":"2025-11-22T17:44:31.762558966Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2025-11-22T17:44:31.771430139Z","level":"INFO","msg":"handleInformInit: received","streamId":"8mhq2ivv","id":"1(@)"}
6
+ {"time":"2025-11-22T17:44:32.14159187Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8mhq2ivv","id":"1(@)"}
7
+ {"time":"2025-11-22T17:52:55.47232209Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8mhq2ivv","id":"1(@)"}
8
+ {"time":"2025-11-22T17:52:55.477411598Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8mhq2ivv","id":"1(@)"}
wandb_logs/run-20251122_174431-8mhq2ivv/logs/debug-internal.log ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2025-11-22T17:44:31.771534275Z","level":"INFO","msg":"stream: starting","core version":"0.23.0"}
2
+ {"time":"2025-11-22T17:44:32.141333974Z","level":"INFO","msg":"stream: created new stream","id":"8mhq2ivv"}
3
+ {"time":"2025-11-22T17:44:32.141411383Z","level":"INFO","msg":"handler: started","stream_id":"8mhq2ivv"}
4
+ {"time":"2025-11-22T17:44:32.141580901Z","level":"INFO","msg":"stream: started","id":"8mhq2ivv"}
5
+ {"time":"2025-11-22T17:44:32.141611972Z","level":"INFO","msg":"writer: started","stream_id":"8mhq2ivv"}
6
+ {"time":"2025-11-22T17:44:32.141632683Z","level":"INFO","msg":"sender: started","stream_id":"8mhq2ivv"}
7
+ {"time":"2025-11-22T17:52:55.145401145Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
8
+ {"time":"2025-11-22T17:52:55.467651839Z","level":"INFO","msg":"handler: operation stats","stats":{}}
9
+ {"time":"2025-11-22T17:52:55.472375271Z","level":"INFO","msg":"stream: closing","id":"8mhq2ivv"}
10
+ {"time":"2025-11-22T17:52:55.472396045Z","level":"INFO","msg":"handler: closed","stream_id":"8mhq2ivv"}
11
+ {"time":"2025-11-22T17:52:55.472483691Z","level":"INFO","msg":"sender: closed","stream_id":"8mhq2ivv"}
12
+ {"time":"2025-11-22T17:52:55.472505222Z","level":"INFO","msg":"stream: closed","id":"8mhq2ivv"}
wandb_logs/run-20251122_174431-8mhq2ivv/logs/debug.log ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Current SDK version is 0.23.0
2
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Configure stats pid to 3693
3
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
4
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Loading settings from /content/code-switch-identification-model/wandb/settings
5
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_setup.py:_flush():80] Loading settings from environment variables
6
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:setup_run_log_directory():713] Logging user logs to /content/code-switch-identification-model/wandb/run-20251122_174431-8mhq2ivv/logs/debug.log
7
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:setup_run_log_directory():714] Logging internal logs to /content/code-switch-identification-model/wandb/run-20251122_174431-8mhq2ivv/logs/debug-internal.log
8
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:init():840] calling init triggers
9
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:init():845] wandb.init called with sweep_config: {}
10
+ config: {'model': 'ai4bharat/indic-bert', 'train_file': 'synthetic_data_gen/data2/train.txt', 'max_length': 128, 'epochs': 3, 'batch_size': 16, 'learning_rate': 2e-05, 'warmup_ratio': 0.1, 'weight_decay': 0.01, '_wandb': {}}
11
+ 2025-11-22 17:44:31,446 INFO MainThread:3693 [wandb_init.py:init():888] starting backend
12
+ 2025-11-22 17:44:31,763 INFO MainThread:3693 [wandb_init.py:init():891] sending inform_init request
13
+ 2025-11-22 17:44:31,767 INFO MainThread:3693 [wandb_init.py:init():899] backend started and connected
14
+ 2025-11-22 17:44:31,774 INFO MainThread:3693 [wandb_init.py:init():969] updated telemetry
15
+ 2025-11-22 17:44:31,793 INFO MainThread:3693 [wandb_init.py:init():993] communicating run to backend with 90.0 second timeout
16
+ 2025-11-22 17:44:32,570 INFO MainThread:3693 [wandb_init.py:init():1040] starting run threads in backend
17
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_console_start():2504] atexit reg
18
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_redirect():2352] redirect: wrap_raw
19
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_redirect():2421] Wrapping output streams.
20
+ 2025-11-22 17:44:33,040 INFO MainThread:3693 [wandb_run.py:_redirect():2444] Redirects installed.
21
+ 2025-11-22 17:44:33,043 INFO MainThread:3693 [wandb_init.py:init():1080] run started, returning control to user process
22
+ 2025-11-22 17:49:59,523 INFO MainThread:3693 [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-data2', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './models/indic-bert-data2/logs', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 50, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': None, 'save_total_limit': 3, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'f1', 'greater_is_better': True, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch_fused', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'h3110Fr13nd/guj-eng-code-switch-indic-bert-data2', 'hub_strategy': 'end', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'guj-eng-code-switch-indic-bert-data2', 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
23
+ 2025-11-22 17:49:59,527 INFO MainThread:3693 [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 0x7f632c2004a0>>
24
+ 2025-11-22 17:49:59,528 INFO MainThread:3693 [wandb_run.py:_config_callback():1385] config_cb model/num_parameters 32856837 None
25
+ 2025-11-22 17:52:53,688 INFO MainThread:3693 [wandb_run.py:_finish():2270] finishing run h3110fr13nd-esparkbiz-technologies-pvt/gujarati-english-code-switch/8mhq2ivv
26
+ 2025-11-22 17:52:53,689 INFO MainThread:3693 [wandb_run.py:_atexit_cleanup():2469] got exitcode: 0
27
+ 2025-11-22 17:52:53,690 INFO MainThread:3693 [wandb_run.py:_restore():2451] restore
28
+ 2025-11-22 17:52:53,690 INFO MainThread:3693 [wandb_run.py:_restore():2457] restore done
29
+ 2025-11-22 17:52:55,471 INFO MainThread:3693 [wandb_run.py:_footer_sync_info():3853] logging synced files
wandb_logs/run-20251122_174431-8mhq2ivv/run-8mhq2ivv.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e889b866aa4674c9464d289acbcf6a21a063077b650a479195746e60e1bb33af
3
+ size 229085