Upload folder using huggingface_hub
Browse files- config.json +50 -0
- label_encoder.joblib +3 -0
- logs/events.out.tfevents.1720068783.9c8bb101f3ea.34.0 +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- vocab.txt +0 -0
- wandb/debug-internal.log +0 -0
- wandb/debug.log +35 -0
- wandb/run-20240704_045325-p1eykagd/files/conda-environment.yaml +0 -0
- wandb/run-20240704_045325-p1eykagd/files/config.yaml +717 -0
- wandb/run-20240704_045325-p1eykagd/files/output.log +4 -0
- wandb/run-20240704_045325-p1eykagd/files/requirements.txt +868 -0
- wandb/run-20240704_045325-p1eykagd/files/wandb-metadata.json +62 -0
- wandb/run-20240704_045325-p1eykagd/files/wandb-summary.json +1 -0
- wandb/run-20240704_045325-p1eykagd/logs/debug-internal.log +0 -0
- wandb/run-20240704_045325-p1eykagd/logs/debug.log +35 -0
- wandb/run-20240704_045325-p1eykagd/run-p1eykagd.wandb +0 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 600,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4,
|
32 |
+
"LABEL_5": 5,
|
33 |
+
"LABEL_6": 6,
|
34 |
+
"LABEL_7": 7,
|
35 |
+
"LABEL_8": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"max_position_embeddings": 2048,
|
39 |
+
"model_type": "bert",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 3,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.41.2",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 83828
|
50 |
+
}
|
label_encoder.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d27c95bec371218940a143acd7bb374065280c3290f685c9427170df213816a6
|
3 |
+
size 729
|
logs/events.out.tfevents.1720068783.9c8bb101f3ea.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca8143a751eec44cee8c10426d048ea7ebaaf375c97cb00829372d36a15429b2
|
3 |
+
size 9090
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66abc2e76867aa45f8ada83bee03155f7620aa3b4391856dc0feac8e71dddf42
|
3 |
+
size 116792900
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 2048,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
wandb/debug-internal.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|
wandb/debug.log
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Current SDK version is 0.17.0
|
2 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Configure stats pid to 34
|
3 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
|
4 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
|
5 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
|
6 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
|
7 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
|
8 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {}
|
9 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
|
10 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:_log_setup():520] Logging user logs to /kaggle/working/wandb/run-20240704_045325-p1eykagd/logs/debug.log
|
11 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:_log_setup():521] Logging internal logs to /kaggle/working/wandb/run-20240704_045325-p1eykagd/logs/debug-internal.log
|
12 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:_jupyter_setup():466] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7d849594c4c0>
|
13 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:init():560] calling init triggers
|
14 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
|
15 |
+
config: {}
|
16 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:init():610] starting backend
|
17 |
+
2024-07-04 04:53:25,911 INFO MainThread:34 [wandb_init.py:init():614] setting up manager
|
18 |
+
2024-07-04 04:53:25,912 INFO MainThread:34 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
|
19 |
+
2024-07-04 04:53:25,915 INFO MainThread:34 [wandb_init.py:init():622] backend started and connected
|
20 |
+
2024-07-04 04:53:25,928 INFO MainThread:34 [wandb_run.py:_label_probe_notebook():1328] probe notebook
|
21 |
+
2024-07-04 04:53:26,473 INFO MainThread:34 [wandb_init.py:init():711] updated telemetry
|
22 |
+
2024-07-04 04:53:26,476 INFO MainThread:34 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
|
23 |
+
2024-07-04 04:53:26,708 INFO MainThread:34 [wandb_run.py:_on_init():2396] communicating current version
|
24 |
+
2024-07-04 04:53:26,790 INFO MainThread:34 [wandb_run.py:_on_init():2405] got version response upgrade_message: "wandb version 0.17.4 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
|
25 |
+
|
26 |
+
2024-07-04 04:53:26,790 INFO MainThread:34 [wandb_init.py:init():795] starting run threads in backend
|
27 |
+
2024-07-04 04:53:42,841 INFO MainThread:34 [wandb_run.py:_console_start():2374] atexit reg
|
28 |
+
2024-07-04 04:53:42,841 INFO MainThread:34 [wandb_run.py:_redirect():2229] redirect: wrap_raw
|
29 |
+
2024-07-04 04:53:42,842 INFO MainThread:34 [wandb_run.py:_redirect():2294] Wrapping output streams.
|
30 |
+
2024-07-04 04:53:42,842 INFO MainThread:34 [wandb_run.py:_redirect():2319] Redirects installed.
|
31 |
+
2024-07-04 04:53:42,846 INFO MainThread:34 [wandb_init.py:init():838] run started, returning control to user process
|
32 |
+
2024-07-04 04:53:42,852 INFO MainThread:34 [wandb_run.py:_config_callback():1376] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BertForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8}, '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, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'cointegrated/rubert-tiny2', 'transformers_version': '4.41.2', 'emb_size': 312, 'gradient_checkpointing': False, 'model_type': 'bert', 'vocab_size': 83828, 'hidden_size': 312, 'num_hidden_layers': 3, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 600, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 2048, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_dir': '/kaggle/working/results', 'overwrite_output_dir': False, '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': 16, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.1, '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': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/logs', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'no', 'save_steps': 500, 'save_total_limit': None, '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, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/results', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'epoch', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False}
|
33 |
+
2024-07-04 06:31:41,429 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
34 |
+
2024-07-04 06:31:41,429 INFO MainThread:34 [wandb_init.py:_pause_backend():431] pausing backend
|
35 |
+
2024-07-04 06:38:44,273 INFO MainThread:34 [wandb_init.py:_resume_backend():436] resuming backend
|
wandb/run-20240704_045325-p1eykagd/files/conda-environment.yaml
ADDED
File without changes
|
wandb/run-20240704_045325-p1eykagd/files/config.yaml
ADDED
@@ -0,0 +1,717 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
wandb_version: 1
|
2 |
+
|
3 |
+
_wandb:
|
4 |
+
desc: null
|
5 |
+
value:
|
6 |
+
python_version: 3.10.13
|
7 |
+
cli_version: 0.17.0
|
8 |
+
framework: huggingface
|
9 |
+
huggingface_version: 4.41.2
|
10 |
+
is_jupyter_run: true
|
11 |
+
is_kaggle_kernel: true
|
12 |
+
start_time: 1720068805
|
13 |
+
t:
|
14 |
+
1:
|
15 |
+
- 1
|
16 |
+
- 2
|
17 |
+
- 3
|
18 |
+
- 5
|
19 |
+
- 11
|
20 |
+
- 12
|
21 |
+
- 49
|
22 |
+
- 51
|
23 |
+
- 53
|
24 |
+
- 55
|
25 |
+
- 71
|
26 |
+
- 105
|
27 |
+
2:
|
28 |
+
- 1
|
29 |
+
- 2
|
30 |
+
- 3
|
31 |
+
- 5
|
32 |
+
- 11
|
33 |
+
- 12
|
34 |
+
- 49
|
35 |
+
- 51
|
36 |
+
- 53
|
37 |
+
- 55
|
38 |
+
- 71
|
39 |
+
- 105
|
40 |
+
3:
|
41 |
+
- 7
|
42 |
+
- 13
|
43 |
+
- 23
|
44 |
+
- 62
|
45 |
+
- 66
|
46 |
+
4: 3.10.13
|
47 |
+
5: 0.17.0
|
48 |
+
6: 4.41.2
|
49 |
+
8:
|
50 |
+
- 1
|
51 |
+
- 2
|
52 |
+
- 5
|
53 |
+
9:
|
54 |
+
1: transformers_trainer
|
55 |
+
13: linux-x86_64
|
56 |
+
m:
|
57 |
+
- 1: train/global_step
|
58 |
+
6:
|
59 |
+
- 3
|
60 |
+
- 1: train/loss
|
61 |
+
5: 1
|
62 |
+
6:
|
63 |
+
- 1
|
64 |
+
- 1: train/grad_norm
|
65 |
+
5: 1
|
66 |
+
6:
|
67 |
+
- 1
|
68 |
+
- 1: train/learning_rate
|
69 |
+
5: 1
|
70 |
+
6:
|
71 |
+
- 1
|
72 |
+
- 1: train/epoch
|
73 |
+
5: 1
|
74 |
+
6:
|
75 |
+
- 1
|
76 |
+
- 1: eval/loss
|
77 |
+
5: 1
|
78 |
+
6:
|
79 |
+
- 1
|
80 |
+
- 1: eval/accuracy
|
81 |
+
5: 1
|
82 |
+
6:
|
83 |
+
- 1
|
84 |
+
- 1: eval/runtime
|
85 |
+
5: 1
|
86 |
+
6:
|
87 |
+
- 1
|
88 |
+
- 1: eval/samples_per_second
|
89 |
+
5: 1
|
90 |
+
6:
|
91 |
+
- 1
|
92 |
+
- 1: eval/steps_per_second
|
93 |
+
5: 1
|
94 |
+
6:
|
95 |
+
- 1
|
96 |
+
return_dict:
|
97 |
+
desc: null
|
98 |
+
value: true
|
99 |
+
output_hidden_states:
|
100 |
+
desc: null
|
101 |
+
value: false
|
102 |
+
output_attentions:
|
103 |
+
desc: null
|
104 |
+
value: false
|
105 |
+
torchscript:
|
106 |
+
desc: null
|
107 |
+
value: false
|
108 |
+
torch_dtype:
|
109 |
+
desc: null
|
110 |
+
value: float32
|
111 |
+
use_bfloat16:
|
112 |
+
desc: null
|
113 |
+
value: false
|
114 |
+
tf_legacy_loss:
|
115 |
+
desc: null
|
116 |
+
value: false
|
117 |
+
pruned_heads:
|
118 |
+
desc: null
|
119 |
+
value: {}
|
120 |
+
tie_word_embeddings:
|
121 |
+
desc: null
|
122 |
+
value: true
|
123 |
+
chunk_size_feed_forward:
|
124 |
+
desc: null
|
125 |
+
value: 0
|
126 |
+
is_encoder_decoder:
|
127 |
+
desc: null
|
128 |
+
value: false
|
129 |
+
is_decoder:
|
130 |
+
desc: null
|
131 |
+
value: false
|
132 |
+
cross_attention_hidden_size:
|
133 |
+
desc: null
|
134 |
+
value: null
|
135 |
+
add_cross_attention:
|
136 |
+
desc: null
|
137 |
+
value: false
|
138 |
+
tie_encoder_decoder:
|
139 |
+
desc: null
|
140 |
+
value: false
|
141 |
+
max_length:
|
142 |
+
desc: null
|
143 |
+
value: 20
|
144 |
+
min_length:
|
145 |
+
desc: null
|
146 |
+
value: 0
|
147 |
+
do_sample:
|
148 |
+
desc: null
|
149 |
+
value: false
|
150 |
+
early_stopping:
|
151 |
+
desc: null
|
152 |
+
value: false
|
153 |
+
num_beams:
|
154 |
+
desc: null
|
155 |
+
value: 1
|
156 |
+
num_beam_groups:
|
157 |
+
desc: null
|
158 |
+
value: 1
|
159 |
+
diversity_penalty:
|
160 |
+
desc: null
|
161 |
+
value: 0.0
|
162 |
+
temperature:
|
163 |
+
desc: null
|
164 |
+
value: 1.0
|
165 |
+
top_k:
|
166 |
+
desc: null
|
167 |
+
value: 50
|
168 |
+
top_p:
|
169 |
+
desc: null
|
170 |
+
value: 1.0
|
171 |
+
typical_p:
|
172 |
+
desc: null
|
173 |
+
value: 1.0
|
174 |
+
repetition_penalty:
|
175 |
+
desc: null
|
176 |
+
value: 1.0
|
177 |
+
length_penalty:
|
178 |
+
desc: null
|
179 |
+
value: 1.0
|
180 |
+
no_repeat_ngram_size:
|
181 |
+
desc: null
|
182 |
+
value: 0
|
183 |
+
encoder_no_repeat_ngram_size:
|
184 |
+
desc: null
|
185 |
+
value: 0
|
186 |
+
bad_words_ids:
|
187 |
+
desc: null
|
188 |
+
value: null
|
189 |
+
num_return_sequences:
|
190 |
+
desc: null
|
191 |
+
value: 1
|
192 |
+
output_scores:
|
193 |
+
desc: null
|
194 |
+
value: false
|
195 |
+
return_dict_in_generate:
|
196 |
+
desc: null
|
197 |
+
value: false
|
198 |
+
forced_bos_token_id:
|
199 |
+
desc: null
|
200 |
+
value: null
|
201 |
+
forced_eos_token_id:
|
202 |
+
desc: null
|
203 |
+
value: null
|
204 |
+
remove_invalid_values:
|
205 |
+
desc: null
|
206 |
+
value: false
|
207 |
+
exponential_decay_length_penalty:
|
208 |
+
desc: null
|
209 |
+
value: null
|
210 |
+
suppress_tokens:
|
211 |
+
desc: null
|
212 |
+
value: null
|
213 |
+
begin_suppress_tokens:
|
214 |
+
desc: null
|
215 |
+
value: null
|
216 |
+
architectures:
|
217 |
+
desc: null
|
218 |
+
value:
|
219 |
+
- BertForPreTraining
|
220 |
+
finetuning_task:
|
221 |
+
desc: null
|
222 |
+
value: null
|
223 |
+
id2label:
|
224 |
+
desc: null
|
225 |
+
value:
|
226 |
+
'0': LABEL_0
|
227 |
+
'1': LABEL_1
|
228 |
+
'2': LABEL_2
|
229 |
+
'3': LABEL_3
|
230 |
+
'4': LABEL_4
|
231 |
+
'5': LABEL_5
|
232 |
+
'6': LABEL_6
|
233 |
+
'7': LABEL_7
|
234 |
+
'8': LABEL_8
|
235 |
+
label2id:
|
236 |
+
desc: null
|
237 |
+
value:
|
238 |
+
LABEL_0: 0
|
239 |
+
LABEL_1: 1
|
240 |
+
LABEL_2: 2
|
241 |
+
LABEL_3: 3
|
242 |
+
LABEL_4: 4
|
243 |
+
LABEL_5: 5
|
244 |
+
LABEL_6: 6
|
245 |
+
LABEL_7: 7
|
246 |
+
LABEL_8: 8
|
247 |
+
tokenizer_class:
|
248 |
+
desc: null
|
249 |
+
value: null
|
250 |
+
prefix:
|
251 |
+
desc: null
|
252 |
+
value: null
|
253 |
+
bos_token_id:
|
254 |
+
desc: null
|
255 |
+
value: null
|
256 |
+
pad_token_id:
|
257 |
+
desc: null
|
258 |
+
value: 0
|
259 |
+
eos_token_id:
|
260 |
+
desc: null
|
261 |
+
value: null
|
262 |
+
sep_token_id:
|
263 |
+
desc: null
|
264 |
+
value: null
|
265 |
+
decoder_start_token_id:
|
266 |
+
desc: null
|
267 |
+
value: null
|
268 |
+
task_specific_params:
|
269 |
+
desc: null
|
270 |
+
value: null
|
271 |
+
problem_type:
|
272 |
+
desc: null
|
273 |
+
value: null
|
274 |
+
_name_or_path:
|
275 |
+
desc: null
|
276 |
+
value: cointegrated/rubert-tiny2
|
277 |
+
transformers_version:
|
278 |
+
desc: null
|
279 |
+
value: 4.41.2
|
280 |
+
emb_size:
|
281 |
+
desc: null
|
282 |
+
value: 312
|
283 |
+
gradient_checkpointing:
|
284 |
+
desc: null
|
285 |
+
value: false
|
286 |
+
model_type:
|
287 |
+
desc: null
|
288 |
+
value: bert
|
289 |
+
vocab_size:
|
290 |
+
desc: null
|
291 |
+
value: 83828
|
292 |
+
hidden_size:
|
293 |
+
desc: null
|
294 |
+
value: 312
|
295 |
+
num_hidden_layers:
|
296 |
+
desc: null
|
297 |
+
value: 3
|
298 |
+
num_attention_heads:
|
299 |
+
desc: null
|
300 |
+
value: 12
|
301 |
+
hidden_act:
|
302 |
+
desc: null
|
303 |
+
value: gelu
|
304 |
+
intermediate_size:
|
305 |
+
desc: null
|
306 |
+
value: 600
|
307 |
+
hidden_dropout_prob:
|
308 |
+
desc: null
|
309 |
+
value: 0.1
|
310 |
+
attention_probs_dropout_prob:
|
311 |
+
desc: null
|
312 |
+
value: 0.1
|
313 |
+
max_position_embeddings:
|
314 |
+
desc: null
|
315 |
+
value: 2048
|
316 |
+
type_vocab_size:
|
317 |
+
desc: null
|
318 |
+
value: 2
|
319 |
+
initializer_range:
|
320 |
+
desc: null
|
321 |
+
value: 0.02
|
322 |
+
layer_norm_eps:
|
323 |
+
desc: null
|
324 |
+
value: 1.0e-12
|
325 |
+
position_embedding_type:
|
326 |
+
desc: null
|
327 |
+
value: absolute
|
328 |
+
use_cache:
|
329 |
+
desc: null
|
330 |
+
value: true
|
331 |
+
classifier_dropout:
|
332 |
+
desc: null
|
333 |
+
value: null
|
334 |
+
output_dir:
|
335 |
+
desc: null
|
336 |
+
value: /kaggle/working/results
|
337 |
+
overwrite_output_dir:
|
338 |
+
desc: null
|
339 |
+
value: false
|
340 |
+
do_train:
|
341 |
+
desc: null
|
342 |
+
value: false
|
343 |
+
do_eval:
|
344 |
+
desc: null
|
345 |
+
value: true
|
346 |
+
do_predict:
|
347 |
+
desc: null
|
348 |
+
value: false
|
349 |
+
eval_strategy:
|
350 |
+
desc: null
|
351 |
+
value: epoch
|
352 |
+
prediction_loss_only:
|
353 |
+
desc: null
|
354 |
+
value: false
|
355 |
+
per_device_train_batch_size:
|
356 |
+
desc: null
|
357 |
+
value: 16
|
358 |
+
per_device_eval_batch_size:
|
359 |
+
desc: null
|
360 |
+
value: 16
|
361 |
+
per_gpu_train_batch_size:
|
362 |
+
desc: null
|
363 |
+
value: null
|
364 |
+
per_gpu_eval_batch_size:
|
365 |
+
desc: null
|
366 |
+
value: null
|
367 |
+
gradient_accumulation_steps:
|
368 |
+
desc: null
|
369 |
+
value: 1
|
370 |
+
eval_accumulation_steps:
|
371 |
+
desc: null
|
372 |
+
value: null
|
373 |
+
eval_delay:
|
374 |
+
desc: null
|
375 |
+
value: 0
|
376 |
+
learning_rate:
|
377 |
+
desc: null
|
378 |
+
value: 1.0e-05
|
379 |
+
weight_decay:
|
380 |
+
desc: null
|
381 |
+
value: 0.1
|
382 |
+
adam_beta1:
|
383 |
+
desc: null
|
384 |
+
value: 0.9
|
385 |
+
adam_beta2:
|
386 |
+
desc: null
|
387 |
+
value: 0.999
|
388 |
+
adam_epsilon:
|
389 |
+
desc: null
|
390 |
+
value: 1.0e-08
|
391 |
+
max_grad_norm:
|
392 |
+
desc: null
|
393 |
+
value: 1.0
|
394 |
+
num_train_epochs:
|
395 |
+
desc: null
|
396 |
+
value: 3
|
397 |
+
max_steps:
|
398 |
+
desc: null
|
399 |
+
value: -1
|
400 |
+
lr_scheduler_type:
|
401 |
+
desc: null
|
402 |
+
value: linear
|
403 |
+
lr_scheduler_kwargs:
|
404 |
+
desc: null
|
405 |
+
value: {}
|
406 |
+
warmup_ratio:
|
407 |
+
desc: null
|
408 |
+
value: 0.0
|
409 |
+
warmup_steps:
|
410 |
+
desc: null
|
411 |
+
value: 0
|
412 |
+
log_level:
|
413 |
+
desc: null
|
414 |
+
value: passive
|
415 |
+
log_level_replica:
|
416 |
+
desc: null
|
417 |
+
value: warning
|
418 |
+
log_on_each_node:
|
419 |
+
desc: null
|
420 |
+
value: true
|
421 |
+
logging_dir:
|
422 |
+
desc: null
|
423 |
+
value: /kaggle/working/logs
|
424 |
+
logging_strategy:
|
425 |
+
desc: null
|
426 |
+
value: steps
|
427 |
+
logging_first_step:
|
428 |
+
desc: null
|
429 |
+
value: false
|
430 |
+
logging_steps:
|
431 |
+
desc: null
|
432 |
+
value: 500
|
433 |
+
logging_nan_inf_filter:
|
434 |
+
desc: null
|
435 |
+
value: true
|
436 |
+
save_strategy:
|
437 |
+
desc: null
|
438 |
+
value: 'no'
|
439 |
+
save_steps:
|
440 |
+
desc: null
|
441 |
+
value: 500
|
442 |
+
save_total_limit:
|
443 |
+
desc: null
|
444 |
+
value: null
|
445 |
+
save_safetensors:
|
446 |
+
desc: null
|
447 |
+
value: true
|
448 |
+
save_on_each_node:
|
449 |
+
desc: null
|
450 |
+
value: false
|
451 |
+
save_only_model:
|
452 |
+
desc: null
|
453 |
+
value: false
|
454 |
+
restore_callback_states_from_checkpoint:
|
455 |
+
desc: null
|
456 |
+
value: false
|
457 |
+
no_cuda:
|
458 |
+
desc: null
|
459 |
+
value: false
|
460 |
+
use_cpu:
|
461 |
+
desc: null
|
462 |
+
value: false
|
463 |
+
use_mps_device:
|
464 |
+
desc: null
|
465 |
+
value: false
|
466 |
+
seed:
|
467 |
+
desc: null
|
468 |
+
value: 42
|
469 |
+
data_seed:
|
470 |
+
desc: null
|
471 |
+
value: null
|
472 |
+
jit_mode_eval:
|
473 |
+
desc: null
|
474 |
+
value: false
|
475 |
+
use_ipex:
|
476 |
+
desc: null
|
477 |
+
value: false
|
478 |
+
bf16:
|
479 |
+
desc: null
|
480 |
+
value: false
|
481 |
+
fp16:
|
482 |
+
desc: null
|
483 |
+
value: false
|
484 |
+
fp16_opt_level:
|
485 |
+
desc: null
|
486 |
+
value: O1
|
487 |
+
half_precision_backend:
|
488 |
+
desc: null
|
489 |
+
value: auto
|
490 |
+
bf16_full_eval:
|
491 |
+
desc: null
|
492 |
+
value: false
|
493 |
+
fp16_full_eval:
|
494 |
+
desc: null
|
495 |
+
value: false
|
496 |
+
tf32:
|
497 |
+
desc: null
|
498 |
+
value: null
|
499 |
+
local_rank:
|
500 |
+
desc: null
|
501 |
+
value: 0
|
502 |
+
ddp_backend:
|
503 |
+
desc: null
|
504 |
+
value: null
|
505 |
+
tpu_num_cores:
|
506 |
+
desc: null
|
507 |
+
value: null
|
508 |
+
tpu_metrics_debug:
|
509 |
+
desc: null
|
510 |
+
value: false
|
511 |
+
debug:
|
512 |
+
desc: null
|
513 |
+
value: []
|
514 |
+
dataloader_drop_last:
|
515 |
+
desc: null
|
516 |
+
value: false
|
517 |
+
eval_steps:
|
518 |
+
desc: null
|
519 |
+
value: null
|
520 |
+
dataloader_num_workers:
|
521 |
+
desc: null
|
522 |
+
value: 0
|
523 |
+
dataloader_prefetch_factor:
|
524 |
+
desc: null
|
525 |
+
value: null
|
526 |
+
past_index:
|
527 |
+
desc: null
|
528 |
+
value: -1
|
529 |
+
run_name:
|
530 |
+
desc: null
|
531 |
+
value: /kaggle/working/results
|
532 |
+
disable_tqdm:
|
533 |
+
desc: null
|
534 |
+
value: false
|
535 |
+
remove_unused_columns:
|
536 |
+
desc: null
|
537 |
+
value: true
|
538 |
+
label_names:
|
539 |
+
desc: null
|
540 |
+
value: null
|
541 |
+
load_best_model_at_end:
|
542 |
+
desc: null
|
543 |
+
value: false
|
544 |
+
metric_for_best_model:
|
545 |
+
desc: null
|
546 |
+
value: null
|
547 |
+
greater_is_better:
|
548 |
+
desc: null
|
549 |
+
value: null
|
550 |
+
ignore_data_skip:
|
551 |
+
desc: null
|
552 |
+
value: false
|
553 |
+
fsdp:
|
554 |
+
desc: null
|
555 |
+
value: []
|
556 |
+
fsdp_min_num_params:
|
557 |
+
desc: null
|
558 |
+
value: 0
|
559 |
+
fsdp_config:
|
560 |
+
desc: null
|
561 |
+
value:
|
562 |
+
min_num_params: 0
|
563 |
+
xla: false
|
564 |
+
xla_fsdp_v2: false
|
565 |
+
xla_fsdp_grad_ckpt: false
|
566 |
+
fsdp_transformer_layer_cls_to_wrap:
|
567 |
+
desc: null
|
568 |
+
value: null
|
569 |
+
accelerator_config:
|
570 |
+
desc: null
|
571 |
+
value:
|
572 |
+
split_batches: false
|
573 |
+
dispatch_batches: null
|
574 |
+
even_batches: true
|
575 |
+
use_seedable_sampler: true
|
576 |
+
non_blocking: false
|
577 |
+
gradient_accumulation_kwargs: null
|
578 |
+
deepspeed:
|
579 |
+
desc: null
|
580 |
+
value: null
|
581 |
+
label_smoothing_factor:
|
582 |
+
desc: null
|
583 |
+
value: 0.0
|
584 |
+
optim:
|
585 |
+
desc: null
|
586 |
+
value: adamw_torch
|
587 |
+
optim_args:
|
588 |
+
desc: null
|
589 |
+
value: null
|
590 |
+
adafactor:
|
591 |
+
desc: null
|
592 |
+
value: false
|
593 |
+
group_by_length:
|
594 |
+
desc: null
|
595 |
+
value: false
|
596 |
+
length_column_name:
|
597 |
+
desc: null
|
598 |
+
value: length
|
599 |
+
report_to:
|
600 |
+
desc: null
|
601 |
+
value:
|
602 |
+
- tensorboard
|
603 |
+
- wandb
|
604 |
+
ddp_find_unused_parameters:
|
605 |
+
desc: null
|
606 |
+
value: null
|
607 |
+
ddp_bucket_cap_mb:
|
608 |
+
desc: null
|
609 |
+
value: null
|
610 |
+
ddp_broadcast_buffers:
|
611 |
+
desc: null
|
612 |
+
value: null
|
613 |
+
dataloader_pin_memory:
|
614 |
+
desc: null
|
615 |
+
value: true
|
616 |
+
dataloader_persistent_workers:
|
617 |
+
desc: null
|
618 |
+
value: false
|
619 |
+
skip_memory_metrics:
|
620 |
+
desc: null
|
621 |
+
value: true
|
622 |
+
use_legacy_prediction_loop:
|
623 |
+
desc: null
|
624 |
+
value: false
|
625 |
+
push_to_hub:
|
626 |
+
desc: null
|
627 |
+
value: false
|
628 |
+
resume_from_checkpoint:
|
629 |
+
desc: null
|
630 |
+
value: null
|
631 |
+
hub_model_id:
|
632 |
+
desc: null
|
633 |
+
value: null
|
634 |
+
hub_strategy:
|
635 |
+
desc: null
|
636 |
+
value: every_save
|
637 |
+
hub_token:
|
638 |
+
desc: null
|
639 |
+
value: <HUB_TOKEN>
|
640 |
+
hub_private_repo:
|
641 |
+
desc: null
|
642 |
+
value: false
|
643 |
+
hub_always_push:
|
644 |
+
desc: null
|
645 |
+
value: false
|
646 |
+
gradient_checkpointing_kwargs:
|
647 |
+
desc: null
|
648 |
+
value: null
|
649 |
+
include_inputs_for_metrics:
|
650 |
+
desc: null
|
651 |
+
value: false
|
652 |
+
eval_do_concat_batches:
|
653 |
+
desc: null
|
654 |
+
value: true
|
655 |
+
fp16_backend:
|
656 |
+
desc: null
|
657 |
+
value: auto
|
658 |
+
evaluation_strategy:
|
659 |
+
desc: null
|
660 |
+
value: epoch
|
661 |
+
push_to_hub_model_id:
|
662 |
+
desc: null
|
663 |
+
value: null
|
664 |
+
push_to_hub_organization:
|
665 |
+
desc: null
|
666 |
+
value: null
|
667 |
+
push_to_hub_token:
|
668 |
+
desc: null
|
669 |
+
value: <PUSH_TO_HUB_TOKEN>
|
670 |
+
mp_parameters:
|
671 |
+
desc: null
|
672 |
+
value: ''
|
673 |
+
auto_find_batch_size:
|
674 |
+
desc: null
|
675 |
+
value: false
|
676 |
+
full_determinism:
|
677 |
+
desc: null
|
678 |
+
value: false
|
679 |
+
torchdynamo:
|
680 |
+
desc: null
|
681 |
+
value: null
|
682 |
+
ray_scope:
|
683 |
+
desc: null
|
684 |
+
value: last
|
685 |
+
ddp_timeout:
|
686 |
+
desc: null
|
687 |
+
value: 1800
|
688 |
+
torch_compile:
|
689 |
+
desc: null
|
690 |
+
value: false
|
691 |
+
torch_compile_backend:
|
692 |
+
desc: null
|
693 |
+
value: null
|
694 |
+
torch_compile_mode:
|
695 |
+
desc: null
|
696 |
+
value: null
|
697 |
+
dispatch_batches:
|
698 |
+
desc: null
|
699 |
+
value: null
|
700 |
+
split_batches:
|
701 |
+
desc: null
|
702 |
+
value: null
|
703 |
+
include_tokens_per_second:
|
704 |
+
desc: null
|
705 |
+
value: false
|
706 |
+
include_num_input_tokens_seen:
|
707 |
+
desc: null
|
708 |
+
value: false
|
709 |
+
neftune_noise_alpha:
|
710 |
+
desc: null
|
711 |
+
value: null
|
712 |
+
optim_target_modules:
|
713 |
+
desc: null
|
714 |
+
value: null
|
715 |
+
batch_eval_metrics:
|
716 |
+
desc: null
|
717 |
+
value: false
|
wandb/run-20240704_045325-p1eykagd/files/output.log
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
Successfully unpacked eval_pred: logits shape (8467, 9), labels shape (8467,)
|
3 |
+
Successfully unpacked eval_pred: logits shape (8467, 9), labels shape (8467,)
|
4 |
+
Successfully unpacked eval_pred: logits shape (8467, 9), labels shape (8467,)
|
wandb/run-20240704_045325-p1eykagd/files/requirements.txt
ADDED
@@ -0,0 +1,868 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Babel==2.14.0
|
2 |
+
Boruta==0.3
|
3 |
+
Brotli==1.1.0
|
4 |
+
CVXcanon==0.1.2
|
5 |
+
Cartopy==0.23.0
|
6 |
+
Cython==3.0.8
|
7 |
+
Deprecated==1.2.14
|
8 |
+
Farama-Notifications==0.0.4
|
9 |
+
Flask==3.0.3
|
10 |
+
Geohash==1.0
|
11 |
+
GitPython==3.1.41
|
12 |
+
ImageHash==4.3.1
|
13 |
+
Janome==0.5.0
|
14 |
+
Jinja2==3.1.2
|
15 |
+
LunarCalendar==0.0.9
|
16 |
+
Mako==1.3.5
|
17 |
+
Markdown==3.5.2
|
18 |
+
MarkupSafe==2.1.3
|
19 |
+
MarkupSafe==2.1.5
|
20 |
+
Pillow==9.5.0
|
21 |
+
PuLP==2.8.0
|
22 |
+
PyArabic==0.6.15
|
23 |
+
PyJWT==2.8.0
|
24 |
+
PyMeeus==0.5.12
|
25 |
+
PySocks==1.7.1
|
26 |
+
PyUpSet==0.1.1.post7
|
27 |
+
PyWavelets==1.5.0
|
28 |
+
PyYAML==6.0.1
|
29 |
+
Pygments==2.17.2
|
30 |
+
Pympler==1.0.1
|
31 |
+
QtPy==2.4.1
|
32 |
+
Rtree==1.2.0
|
33 |
+
SQLAlchemy==2.0.25
|
34 |
+
SecretStorage==3.3.3
|
35 |
+
Send2Trash==1.8.2
|
36 |
+
Shapely==1.8.5.post1
|
37 |
+
Shimmy==1.3.0
|
38 |
+
SimpleITK==2.3.1
|
39 |
+
TPOT==0.12.1
|
40 |
+
Theano-PyMC==1.1.2
|
41 |
+
Theano==1.0.5
|
42 |
+
Wand==0.6.13
|
43 |
+
Werkzeug==3.0.3
|
44 |
+
absl-py==1.4.0
|
45 |
+
accelerate==0.30.1
|
46 |
+
access==1.1.9
|
47 |
+
affine==2.4.0
|
48 |
+
aiobotocore==2.13.0
|
49 |
+
aiofiles==22.1.0
|
50 |
+
aiohttp==3.9.1
|
51 |
+
aioitertools==0.11.0
|
52 |
+
aiorwlock==1.3.0
|
53 |
+
aiosignal==1.3.1
|
54 |
+
aiosqlite==0.19.0
|
55 |
+
albumentations==1.4.0
|
56 |
+
alembic==1.13.1
|
57 |
+
altair==5.3.0
|
58 |
+
annotated-types==0.6.0
|
59 |
+
annotated-types==0.7.0
|
60 |
+
annoy==1.17.3
|
61 |
+
anyio==4.2.0
|
62 |
+
apache-beam==2.46.0
|
63 |
+
aplus==0.11.0
|
64 |
+
appdirs==1.4.4
|
65 |
+
archspec==0.2.3
|
66 |
+
argon2-cffi-bindings==21.2.0
|
67 |
+
argon2-cffi==23.1.0
|
68 |
+
array-record==0.5.0
|
69 |
+
arrow==1.3.0
|
70 |
+
arviz==0.18.0
|
71 |
+
astroid==3.2.2
|
72 |
+
astropy-iers-data==0.2024.6.3.0.31.14
|
73 |
+
astropy==6.1.0
|
74 |
+
asttokens==2.4.1
|
75 |
+
astunparse==1.6.3
|
76 |
+
async-lru==2.0.4
|
77 |
+
async-timeout==4.0.3
|
78 |
+
attrs==23.2.0
|
79 |
+
audioread==3.0.1
|
80 |
+
autopep8==2.0.4
|
81 |
+
backoff==2.2.1
|
82 |
+
bayesian-optimization==1.4.3
|
83 |
+
beatrix_jupyterlab==2023.128.151533
|
84 |
+
beautifulsoup4==4.12.2
|
85 |
+
blake3==0.2.1
|
86 |
+
bleach==6.1.0
|
87 |
+
blessed==1.20.0
|
88 |
+
blinker==1.8.2
|
89 |
+
blis==0.7.10
|
90 |
+
blosc2==2.6.2
|
91 |
+
bokeh==3.4.1
|
92 |
+
boltons==23.1.1
|
93 |
+
boto3==1.26.100
|
94 |
+
botocore==1.34.106
|
95 |
+
bq_helper==0.4.1
|
96 |
+
bqplot==0.12.43
|
97 |
+
branca==0.7.2
|
98 |
+
brewer2mpl==1.4.1
|
99 |
+
brotlipy==0.7.0
|
100 |
+
cached-property==1.5.2
|
101 |
+
cachetools==4.2.4
|
102 |
+
cachetools==5.3.2
|
103 |
+
catalogue==2.0.10
|
104 |
+
catalyst==22.4
|
105 |
+
catboost==1.2.5
|
106 |
+
category-encoders==2.6.3
|
107 |
+
certifi==2024.2.2
|
108 |
+
cesium==0.12.1
|
109 |
+
cffi==1.16.0
|
110 |
+
charset-normalizer==3.3.2
|
111 |
+
chex==0.1.86
|
112 |
+
cleverhans==4.0.0
|
113 |
+
click-plugins==1.1.1
|
114 |
+
click==8.1.7
|
115 |
+
cligj==0.7.2
|
116 |
+
cloud-tpu-client==0.10
|
117 |
+
cloud-tpu-profiler==2.4.0
|
118 |
+
cloudpathlib==0.16.0
|
119 |
+
cloudpickle==2.2.1
|
120 |
+
cloudpickle==3.0.0
|
121 |
+
cmdstanpy==1.2.3
|
122 |
+
colorama==0.4.6
|
123 |
+
colorcet==3.1.0
|
124 |
+
colorful==0.5.6
|
125 |
+
colorlog==6.8.2
|
126 |
+
colorlover==0.3.0
|
127 |
+
comm==0.2.1
|
128 |
+
conda-libmamba-solver==23.12.0
|
129 |
+
conda-package-handling==2.2.0
|
130 |
+
conda==24.5.0
|
131 |
+
conda_package_streaming==0.9.0
|
132 |
+
confection==0.1.4
|
133 |
+
contextily==1.6.0
|
134 |
+
contourpy==1.2.0
|
135 |
+
contourpy==1.2.1
|
136 |
+
convertdate==2.4.0
|
137 |
+
crcmod==1.7
|
138 |
+
cryptography==41.0.7
|
139 |
+
cuda-python==12.5.0
|
140 |
+
cudf==24.4.1
|
141 |
+
cufflinks==0.17.3
|
142 |
+
cuml==24.4.0
|
143 |
+
cupy==13.1.0
|
144 |
+
cycler==0.12.1
|
145 |
+
cymem==2.0.8
|
146 |
+
cytoolz==0.12.3
|
147 |
+
daal4py==2024.4.0
|
148 |
+
daal==2024.4.0
|
149 |
+
dacite==1.8.1
|
150 |
+
dask-cuda==24.4.0
|
151 |
+
dask-cudf==24.4.1
|
152 |
+
dask-expr==1.1.2
|
153 |
+
dask==2024.5.2
|
154 |
+
dataclasses-json==0.6.6
|
155 |
+
dataproc_jupyter_plugin==0.1.66
|
156 |
+
datasets==2.19.2
|
157 |
+
datashader==0.16.2
|
158 |
+
datatile==1.0.3
|
159 |
+
db-dtypes==1.2.0
|
160 |
+
deap==1.4.1
|
161 |
+
debugpy==1.8.0
|
162 |
+
decorator==5.1.1
|
163 |
+
deepdiff==7.0.1
|
164 |
+
defusedxml==0.7.1
|
165 |
+
deprecation==2.1.0
|
166 |
+
descartes==1.1.0
|
167 |
+
dill==0.3.8
|
168 |
+
dipy==1.9.0
|
169 |
+
distlib==0.3.8
|
170 |
+
distributed==2024.1.1
|
171 |
+
distro==1.9.0
|
172 |
+
dm-tree==0.1.8
|
173 |
+
docker-pycreds==0.4.0
|
174 |
+
docker==7.0.0
|
175 |
+
docopt==0.6.2
|
176 |
+
docstring-parser==0.15
|
177 |
+
docstring-to-markdown==0.15
|
178 |
+
docutils==0.21.2
|
179 |
+
earthengine-api==0.1.405
|
180 |
+
easydict==1.13
|
181 |
+
easyocr==1.7.1
|
182 |
+
ecos==2.0.13
|
183 |
+
eli5==0.13.0
|
184 |
+
emoji==2.12.1
|
185 |
+
en-core-web-lg==3.7.1
|
186 |
+
en-core-web-sm==3.7.1
|
187 |
+
entrypoints==0.4
|
188 |
+
ephem==4.1.5
|
189 |
+
esda==2.5.1
|
190 |
+
essentia==2.1b6.dev1110
|
191 |
+
et-xmlfile==1.1.0
|
192 |
+
etils==1.6.0
|
193 |
+
exceptiongroup==1.2.0
|
194 |
+
executing==2.0.1
|
195 |
+
explainable-ai-sdk==1.3.3
|
196 |
+
fastai==2.7.15
|
197 |
+
fastapi==0.108.0
|
198 |
+
fastavro==1.9.3
|
199 |
+
fastcore==1.5.43
|
200 |
+
fastdownload==0.0.7
|
201 |
+
fasteners==0.19
|
202 |
+
fastjsonschema==2.19.1
|
203 |
+
fastprogress==1.0.3
|
204 |
+
fastrlock==0.8.2
|
205 |
+
fasttext==0.9.2
|
206 |
+
feather-format==0.4.1
|
207 |
+
featuretools==1.31.0
|
208 |
+
filelock==3.13.1
|
209 |
+
fiona==1.9.6
|
210 |
+
fitter==1.7.0
|
211 |
+
flake8==7.0.0
|
212 |
+
flashtext==2.7
|
213 |
+
flatbuffers==23.5.26
|
214 |
+
flax==0.8.4
|
215 |
+
folium==0.16.0
|
216 |
+
fonttools==4.47.0
|
217 |
+
fonttools==4.53.0
|
218 |
+
fqdn==1.5.1
|
219 |
+
frozendict==2.4.4
|
220 |
+
frozenlist==1.4.1
|
221 |
+
fsspec==2024.3.1
|
222 |
+
fsspec==2024.5.0
|
223 |
+
funcy==2.0
|
224 |
+
fury==0.10.0
|
225 |
+
future==1.0.0
|
226 |
+
fuzzywuzzy==0.18.0
|
227 |
+
gast==0.5.4
|
228 |
+
gatspy==0.3
|
229 |
+
gcsfs==2024.3.1
|
230 |
+
gensim==4.3.2
|
231 |
+
geographiclib==2.0
|
232 |
+
geojson==3.1.0
|
233 |
+
geopandas==0.14.4
|
234 |
+
geoplot==0.5.1
|
235 |
+
geopy==2.4.1
|
236 |
+
geoviews==1.12.0
|
237 |
+
ggplot==0.11.5
|
238 |
+
giddy==2.3.5
|
239 |
+
gitdb==4.0.11
|
240 |
+
google-ai-generativelanguage==0.6.4
|
241 |
+
google-api-core==2.11.1
|
242 |
+
google-api-core==2.19.0
|
243 |
+
google-api-python-client==2.131.0
|
244 |
+
google-apitools==0.5.31
|
245 |
+
google-auth-httplib2==0.2.0
|
246 |
+
google-auth-oauthlib==1.2.0
|
247 |
+
google-auth==2.26.1
|
248 |
+
google-cloud-aiplatform==0.6.0a1
|
249 |
+
google-cloud-artifact-registry==1.10.0
|
250 |
+
google-cloud-automl==1.0.1
|
251 |
+
google-cloud-bigquery==2.34.4
|
252 |
+
google-cloud-bigtable==1.7.3
|
253 |
+
google-cloud-core==2.4.1
|
254 |
+
google-cloud-datastore==2.19.0
|
255 |
+
google-cloud-dlp==3.14.0
|
256 |
+
google-cloud-jupyter-config==0.0.5
|
257 |
+
google-cloud-language==2.13.3
|
258 |
+
google-cloud-monitoring==2.18.0
|
259 |
+
google-cloud-pubsub==2.19.0
|
260 |
+
google-cloud-pubsublite==1.9.0
|
261 |
+
google-cloud-recommendations-ai==0.7.1
|
262 |
+
google-cloud-resource-manager==1.11.0
|
263 |
+
google-cloud-spanner==3.40.1
|
264 |
+
google-cloud-storage==1.44.0
|
265 |
+
google-cloud-translate==3.12.1
|
266 |
+
google-cloud-videointelligence==2.13.3
|
267 |
+
google-cloud-vision==2.8.0
|
268 |
+
google-crc32c==1.5.0
|
269 |
+
google-generativeai==0.6.0
|
270 |
+
google-pasta==0.2.0
|
271 |
+
google-resumable-media==2.7.0
|
272 |
+
googleapis-common-protos==1.62.0
|
273 |
+
gplearn==0.4.2
|
274 |
+
gpustat==1.0.0
|
275 |
+
gpxpy==1.6.2
|
276 |
+
graphviz==0.20.3
|
277 |
+
greenlet==3.0.3
|
278 |
+
grpc-google-iam-v1==0.12.7
|
279 |
+
grpcio-status==1.48.1
|
280 |
+
grpcio-status==1.48.2
|
281 |
+
grpcio==1.59.3
|
282 |
+
grpcio==1.60.0
|
283 |
+
gviz-api==1.10.0
|
284 |
+
gym-notices==0.0.8
|
285 |
+
gym==0.26.2
|
286 |
+
gymnasium==0.29.0
|
287 |
+
h11==0.14.0
|
288 |
+
h2o==3.46.0.2
|
289 |
+
h5netcdf==1.3.0
|
290 |
+
h5py==3.10.0
|
291 |
+
haversine==2.8.1
|
292 |
+
hdfs==2.7.3
|
293 |
+
hep-ml==0.7.2
|
294 |
+
hijri-converter==2.3.1
|
295 |
+
hmmlearn==0.3.2
|
296 |
+
holidays==0.24
|
297 |
+
holoviews==1.18.3
|
298 |
+
hpsklearn==0.1.0
|
299 |
+
html5lib==1.1
|
300 |
+
htmlmin==0.1.12
|
301 |
+
httpcore==1.0.5
|
302 |
+
httplib2==0.21.0
|
303 |
+
httptools==0.6.1
|
304 |
+
httpx==0.27.0
|
305 |
+
huggingface-hub==0.23.2
|
306 |
+
hunspell==0.5.5
|
307 |
+
hydra-slayer==0.5.0
|
308 |
+
hyperopt==0.2.7
|
309 |
+
hypertools==0.8.0
|
310 |
+
idna==3.6
|
311 |
+
igraph==0.11.5
|
312 |
+
imagecodecs==2024.6.1
|
313 |
+
imageio==2.33.1
|
314 |
+
imbalanced-learn==0.12.3
|
315 |
+
imgaug==0.4.0
|
316 |
+
importlib-metadata==6.11.0
|
317 |
+
importlib-metadata==7.0.1
|
318 |
+
importlib-resources==6.1.1
|
319 |
+
inequality==1.0.1
|
320 |
+
iniconfig==2.0.0
|
321 |
+
ipydatawidgets==4.3.5
|
322 |
+
ipykernel==6.28.0
|
323 |
+
ipyleaflet==0.19.1
|
324 |
+
ipympl==0.7.0
|
325 |
+
ipython-genutils==0.2.0
|
326 |
+
ipython-genutils==0.2.0
|
327 |
+
ipython-sql==0.5.0
|
328 |
+
ipython==8.20.0
|
329 |
+
ipyvolume==0.6.3
|
330 |
+
ipyvue==1.11.1
|
331 |
+
ipyvuetify==1.9.4
|
332 |
+
ipywebrtc==0.6.0
|
333 |
+
ipywidgets==7.7.1
|
334 |
+
isoduration==20.11.0
|
335 |
+
isort==5.13.2
|
336 |
+
isoweek==1.3.3
|
337 |
+
itsdangerous==2.2.0
|
338 |
+
jaraco.classes==3.3.0
|
339 |
+
jax-jumpy==1.0.0
|
340 |
+
jax==0.4.26
|
341 |
+
jaxlib==0.4.26.dev20240504
|
342 |
+
jedi==0.19.1
|
343 |
+
jeepney==0.8.0
|
344 |
+
jieba==0.42.1
|
345 |
+
jmespath==1.0.1
|
346 |
+
joblib==1.4.2
|
347 |
+
json5==0.9.14
|
348 |
+
jsonpatch==1.33
|
349 |
+
jsonpointer==2.4
|
350 |
+
jsonschema-specifications==2023.12.1
|
351 |
+
jsonschema==4.20.0
|
352 |
+
jupyter-console==6.6.3
|
353 |
+
jupyter-events==0.9.0
|
354 |
+
jupyter-http-over-ws==0.0.8
|
355 |
+
jupyter-leaflet==0.19.1
|
356 |
+
jupyter-lsp==1.5.1
|
357 |
+
jupyter-server-mathjax==0.2.6
|
358 |
+
jupyter-ydoc==0.2.5
|
359 |
+
jupyter_client==7.4.9
|
360 |
+
jupyter_client==8.6.0
|
361 |
+
jupyter_core==5.7.1
|
362 |
+
jupyter_server==2.12.5
|
363 |
+
jupyter_server_fileid==0.9.1
|
364 |
+
jupyter_server_proxy==4.1.0
|
365 |
+
jupyter_server_terminals==0.5.1
|
366 |
+
jupyter_server_ydoc==0.8.0
|
367 |
+
jupyterlab-lsp==5.1.0
|
368 |
+
jupyterlab-widgets==3.0.9
|
369 |
+
jupyterlab==4.2.1
|
370 |
+
jupyterlab_git==0.44.0
|
371 |
+
jupyterlab_pygments==0.3.0
|
372 |
+
jupyterlab_server==2.27.2
|
373 |
+
jupytext==1.16.0
|
374 |
+
kaggle-environments==1.14.11
|
375 |
+
kaggle==1.6.14
|
376 |
+
kagglehub==0.2.5
|
377 |
+
keras-cv==0.9.0
|
378 |
+
keras-nlp==0.12.1
|
379 |
+
keras-tuner==1.4.6
|
380 |
+
keras==3.3.3
|
381 |
+
kernels-mixer==0.0.7
|
382 |
+
keyring==24.3.0
|
383 |
+
keyrings.google-artifactregistry-auth==1.1.2
|
384 |
+
kfp-pipeline-spec==0.2.2
|
385 |
+
kfp-server-api==2.0.5
|
386 |
+
kfp==2.5.0
|
387 |
+
kiwisolver==1.4.5
|
388 |
+
kmapper==2.0.1
|
389 |
+
kmodes==0.12.2
|
390 |
+
korean-lunar-calendar==0.3.1
|
391 |
+
kornia==0.7.2
|
392 |
+
kornia_rs==0.1.3
|
393 |
+
kt-legacy==1.0.5
|
394 |
+
kubernetes==26.1.0
|
395 |
+
langcodes==3.4.0
|
396 |
+
langid==1.1.6
|
397 |
+
language_data==1.2.0
|
398 |
+
lazy_loader==0.3
|
399 |
+
learntools==0.3.4
|
400 |
+
leven==1.0.4
|
401 |
+
libclang==16.0.6
|
402 |
+
libmambapy==1.5.8
|
403 |
+
libpysal==4.9.2
|
404 |
+
librosa==0.10.2.post1
|
405 |
+
lightgbm==4.2.0
|
406 |
+
lightning-utilities==0.11.2
|
407 |
+
lime==0.2.0.1
|
408 |
+
line_profiler==4.1.3
|
409 |
+
linkify-it-py==2.0.3
|
410 |
+
llvmlite==0.41.1
|
411 |
+
llvmlite==0.42.0
|
412 |
+
lml==0.1.0
|
413 |
+
locket==1.0.0
|
414 |
+
loguru==0.7.2
|
415 |
+
lxml==5.2.2
|
416 |
+
lz4==4.3.3
|
417 |
+
mamba==1.5.8
|
418 |
+
mapclassify==2.6.1
|
419 |
+
marisa-trie==1.1.0
|
420 |
+
markdown-it-py==3.0.0
|
421 |
+
marshmallow==3.21.2
|
422 |
+
matplotlib-inline==0.1.6
|
423 |
+
matplotlib-venn==0.11.10
|
424 |
+
matplotlib==3.7.5
|
425 |
+
matplotlib==3.8.4
|
426 |
+
mccabe==0.7.0
|
427 |
+
mdit-py-plugins==0.4.0
|
428 |
+
mdurl==0.1.2
|
429 |
+
memory-profiler==0.61.0
|
430 |
+
menuinst==2.0.1
|
431 |
+
mercantile==1.2.1
|
432 |
+
mgwr==2.2.1
|
433 |
+
missingno==0.5.2
|
434 |
+
mistune==0.8.4
|
435 |
+
mizani==0.11.4
|
436 |
+
ml-dtypes==0.2.0
|
437 |
+
mlcrate==0.2.0
|
438 |
+
mlens==0.2.3
|
439 |
+
mlxtend==0.23.1
|
440 |
+
mne==1.7.0
|
441 |
+
mnist==0.2.2
|
442 |
+
momepy==0.7.0
|
443 |
+
more-itertools==10.2.0
|
444 |
+
mpld3==0.5.10
|
445 |
+
mpmath==1.3.0
|
446 |
+
msgpack==1.0.7
|
447 |
+
msgpack==1.0.8
|
448 |
+
multidict==6.0.4
|
449 |
+
multimethod==1.10
|
450 |
+
multipledispatch==1.0.0
|
451 |
+
multiprocess==0.70.16
|
452 |
+
munkres==1.1.4
|
453 |
+
murmurhash==1.0.10
|
454 |
+
mypy-extensions==1.0.0
|
455 |
+
namex==0.0.8
|
456 |
+
nb-conda-kernels==2.3.1
|
457 |
+
nb_conda==2.2.1
|
458 |
+
nbclassic==1.0.0
|
459 |
+
nbclient==0.5.13
|
460 |
+
nbclient==0.9.0
|
461 |
+
nbconvert==6.4.5
|
462 |
+
nbdime==3.2.0
|
463 |
+
nbformat==5.9.2
|
464 |
+
ndindex==1.8
|
465 |
+
nest-asyncio==1.5.8
|
466 |
+
networkx==3.2.1
|
467 |
+
nibabel==5.2.1
|
468 |
+
nilearn==0.10.4
|
469 |
+
ninja==1.11.1.1
|
470 |
+
nltk==3.2.4
|
471 |
+
nose==1.3.7
|
472 |
+
notebook==6.5.4
|
473 |
+
notebook==6.5.6
|
474 |
+
notebook_executor==0.2
|
475 |
+
notebook_shim==0.2.3
|
476 |
+
numba==0.58.1
|
477 |
+
numba==0.59.1
|
478 |
+
numexpr==2.10.0
|
479 |
+
numpy==1.26.4
|
480 |
+
nvidia-ml-py==11.495.46
|
481 |
+
nvtx==0.2.10
|
482 |
+
oauth2client==4.1.3
|
483 |
+
oauthlib==3.2.2
|
484 |
+
objsize==0.6.1
|
485 |
+
odfpy==1.4.1
|
486 |
+
olefile==0.47
|
487 |
+
onnx==1.16.1
|
488 |
+
opencensus-context==0.1.3
|
489 |
+
opencensus==0.11.4
|
490 |
+
opencv-contrib-python==4.10.0.82
|
491 |
+
opencv-python-headless==4.10.0.82
|
492 |
+
opencv-python==4.10.0.82
|
493 |
+
openpyxl==3.1.3
|
494 |
+
openslide-python==1.3.1
|
495 |
+
opentelemetry-api==1.22.0
|
496 |
+
opentelemetry-exporter-otlp-proto-common==1.22.0
|
497 |
+
opentelemetry-exporter-otlp-proto-grpc==1.22.0
|
498 |
+
opentelemetry-exporter-otlp-proto-http==1.22.0
|
499 |
+
opentelemetry-exporter-otlp==1.22.0
|
500 |
+
opentelemetry-proto==1.22.0
|
501 |
+
opentelemetry-sdk==1.22.0
|
502 |
+
opentelemetry-semantic-conventions==0.43b0
|
503 |
+
opt-einsum==3.3.0
|
504 |
+
optax==0.2.2
|
505 |
+
optree==0.11.0
|
506 |
+
optuna==3.6.1
|
507 |
+
orbax-checkpoint==0.5.15
|
508 |
+
ordered-set==4.1.0
|
509 |
+
orjson==3.9.10
|
510 |
+
ortools==9.4.1874
|
511 |
+
osmnx==1.9.3
|
512 |
+
overrides==7.4.0
|
513 |
+
packaging==21.3
|
514 |
+
pandas-datareader==0.10.0
|
515 |
+
pandas-profiling==3.6.6
|
516 |
+
pandas-summary==0.2.0
|
517 |
+
pandas==2.2.1
|
518 |
+
pandas==2.2.2
|
519 |
+
pandasql==0.7.3
|
520 |
+
pandocfilters==1.5.0
|
521 |
+
panel==1.4.4
|
522 |
+
papermill==2.5.0
|
523 |
+
param==2.1.0
|
524 |
+
parso==0.8.3
|
525 |
+
partd==1.4.2
|
526 |
+
path.py==12.5.0
|
527 |
+
path==16.14.0
|
528 |
+
pathos==0.3.2
|
529 |
+
pathy==0.10.3
|
530 |
+
patsy==0.5.6
|
531 |
+
pdf2image==1.17.0
|
532 |
+
pettingzoo==1.24.0
|
533 |
+
pexpect==4.8.0
|
534 |
+
pexpect==4.9.0
|
535 |
+
phik==0.12.4
|
536 |
+
pickleshare==0.7.5
|
537 |
+
pillow==10.3.0
|
538 |
+
pip==23.3.2
|
539 |
+
pkgutil_resolve_name==1.3.10
|
540 |
+
platformdirs==3.11.0
|
541 |
+
platformdirs==4.1.0
|
542 |
+
plotly-express==0.4.1
|
543 |
+
plotly==5.18.0
|
544 |
+
plotnine==0.13.6
|
545 |
+
pluggy==1.5.0
|
546 |
+
pointpats==2.4.0
|
547 |
+
polars==0.20.31
|
548 |
+
polyglot==16.7.4
|
549 |
+
pooch==1.8.1
|
550 |
+
pox==0.3.4
|
551 |
+
ppca==0.0.4
|
552 |
+
ppft==1.7.6.8
|
553 |
+
preprocessing==0.1.13
|
554 |
+
preshed==3.0.9
|
555 |
+
prettytable==3.9.0
|
556 |
+
progressbar2==4.4.2
|
557 |
+
prometheus-client==0.19.0
|
558 |
+
promise==2.3
|
559 |
+
prompt-toolkit==3.0.42
|
560 |
+
prompt-toolkit==3.0.43
|
561 |
+
prophet==1.1.1
|
562 |
+
proto-plus==1.23.0
|
563 |
+
protobuf==3.20.3
|
564 |
+
protobuf==4.24.4
|
565 |
+
psutil==5.9.3
|
566 |
+
psutil==5.9.7
|
567 |
+
ptyprocess==0.7.0
|
568 |
+
pudb==2024.1
|
569 |
+
pure-eval==0.2.2
|
570 |
+
py-cpuinfo==9.0.0
|
571 |
+
py-spy==0.3.14
|
572 |
+
py4j==0.10.9.7
|
573 |
+
pyLDAvis==3.4.1
|
574 |
+
pyOpenSSL==23.3.0
|
575 |
+
pyaml==24.4.0
|
576 |
+
pyarrow-hotfix==0.6
|
577 |
+
pyarrow==14.0.2
|
578 |
+
pyasn1-modules==0.3.0
|
579 |
+
pyasn1==0.5.1
|
580 |
+
pybind11==2.12.0
|
581 |
+
pyclipper==1.3.0.post5
|
582 |
+
pycodestyle==2.11.1
|
583 |
+
pycosat==0.6.6
|
584 |
+
pycparser==2.21
|
585 |
+
pycryptodome==3.20.0
|
586 |
+
pyct==0.5.0
|
587 |
+
pycuda==2024.1
|
588 |
+
pydantic==2.5.3
|
589 |
+
pydantic==2.7.2
|
590 |
+
pydantic_core==2.14.6
|
591 |
+
pydantic_core==2.18.3
|
592 |
+
pydegensac==0.1.2
|
593 |
+
pydicom==2.4.4
|
594 |
+
pydocstyle==6.3.0
|
595 |
+
pydot==1.4.2
|
596 |
+
pydub==0.25.1
|
597 |
+
pyemd==1.0.0
|
598 |
+
pyerfa==2.0.1.4
|
599 |
+
pyexcel-io==0.6.6
|
600 |
+
pyexcel-ods==0.6.0
|
601 |
+
pyflakes==3.2.0
|
602 |
+
pygltflib==1.16.2
|
603 |
+
pykalman==0.9.7
|
604 |
+
pylibraft==24.4.0
|
605 |
+
pylint==3.2.2
|
606 |
+
pymc3==3.11.4
|
607 |
+
pymongo==3.13.0
|
608 |
+
pynndescent==0.5.12
|
609 |
+
pynvjitlink==0.2.3
|
610 |
+
pynvml==11.4.1
|
611 |
+
pynvrtc==9.2
|
612 |
+
pyparsing==3.1.1
|
613 |
+
pyparsing==3.1.2
|
614 |
+
pypdf==4.2.0
|
615 |
+
pyproj==3.6.1
|
616 |
+
pysal==24.1
|
617 |
+
pyshp==2.3.1
|
618 |
+
pytesseract==0.3.10
|
619 |
+
pytest==8.2.1
|
620 |
+
python-bidi==0.4.2
|
621 |
+
python-dateutil==2.9.0.post0
|
622 |
+
python-dotenv==1.0.0
|
623 |
+
python-json-logger==2.0.7
|
624 |
+
python-louvain==0.16
|
625 |
+
python-lsp-jsonrpc==1.1.2
|
626 |
+
python-lsp-server==1.11.0
|
627 |
+
python-slugify==8.0.4
|
628 |
+
python-utils==3.8.2
|
629 |
+
pythreejs==2.4.2
|
630 |
+
pytoolconfig==1.3.1
|
631 |
+
pytools==2024.1.3
|
632 |
+
pytorch-ignite==0.5.0.post2
|
633 |
+
pytorch-lightning==2.2.5
|
634 |
+
pytz==2023.3.post1
|
635 |
+
pytz==2024.1
|
636 |
+
pyu2f==0.1.5
|
637 |
+
pyviz_comms==3.0.2
|
638 |
+
pyzmq==24.0.1
|
639 |
+
pyzmq==25.1.2
|
640 |
+
qgrid==1.3.1
|
641 |
+
qtconsole==5.5.2
|
642 |
+
quantecon==0.7.2
|
643 |
+
qudida==0.0.4
|
644 |
+
raft-dask==24.4.0
|
645 |
+
rapids-dask-dependency==24.4.1a0
|
646 |
+
rasterio==1.3.10
|
647 |
+
rasterstats==0.19.0
|
648 |
+
ray-cpp==2.9.0
|
649 |
+
ray==2.9.0
|
650 |
+
referencing==0.32.1
|
651 |
+
regex==2023.12.25
|
652 |
+
requests-oauthlib==1.3.1
|
653 |
+
requests-toolbelt==0.10.1
|
654 |
+
requests==2.32.3
|
655 |
+
retrying==1.3.3
|
656 |
+
retrying==1.3.4
|
657 |
+
rfc3339-validator==0.1.4
|
658 |
+
rfc3986-validator==0.1.1
|
659 |
+
rgf-python==3.12.0
|
660 |
+
rich-click==1.8.2
|
661 |
+
rich==13.7.0
|
662 |
+
rich==13.7.1
|
663 |
+
rmm==24.4.0
|
664 |
+
rope==1.13.0
|
665 |
+
rpds-py==0.16.2
|
666 |
+
rsa==4.9
|
667 |
+
ruamel-yaml-conda==0.15.100
|
668 |
+
ruamel.yaml.clib==0.2.7
|
669 |
+
ruamel.yaml==0.18.5
|
670 |
+
s2sphere==0.2.5
|
671 |
+
s3fs==2024.3.1
|
672 |
+
s3transfer==0.6.2
|
673 |
+
safetensors==0.4.3
|
674 |
+
scattertext==0.1.19
|
675 |
+
scikit-image==0.22.0
|
676 |
+
scikit-learn-intelex==2024.4.0
|
677 |
+
scikit-learn==1.2.2
|
678 |
+
scikit-multilearn==0.2.0
|
679 |
+
scikit-optimize==0.10.1
|
680 |
+
scikit-plot==0.3.7
|
681 |
+
scikit-surprise==1.1.4
|
682 |
+
scipy==1.11.4
|
683 |
+
scipy==1.13.1
|
684 |
+
seaborn==0.12.2
|
685 |
+
segment_anything==1.0
|
686 |
+
segregation==2.5
|
687 |
+
semver==3.0.2
|
688 |
+
sentencepiece==0.2.0
|
689 |
+
sentry-sdk==2.3.1
|
690 |
+
setproctitle==1.3.3
|
691 |
+
setuptools-git==1.2
|
692 |
+
setuptools-scm==8.1.0
|
693 |
+
setuptools==69.0.3
|
694 |
+
shap==0.44.1
|
695 |
+
shapely==2.0.4
|
696 |
+
shellingham==1.5.4
|
697 |
+
simpervisor==1.0.0
|
698 |
+
simplejson==3.19.2
|
699 |
+
six==1.16.0
|
700 |
+
sklearn-pandas==2.2.0
|
701 |
+
slicer==0.0.7
|
702 |
+
smart-open==6.4.0
|
703 |
+
smmap==5.0.1
|
704 |
+
sniffio==1.3.0
|
705 |
+
snowballstemmer==2.2.0
|
706 |
+
snuggs==1.4.7
|
707 |
+
sortedcontainers==2.4.0
|
708 |
+
soundfile==0.12.1
|
709 |
+
soupsieve==2.5
|
710 |
+
soxr==0.3.7
|
711 |
+
spacy-legacy==3.0.12
|
712 |
+
spacy-loggers==1.0.5
|
713 |
+
spacy==3.7.3
|
714 |
+
spaghetti==1.7.5.post1
|
715 |
+
spectral==0.23.1
|
716 |
+
spglm==1.1.0
|
717 |
+
sphinx-rtd-theme==0.2.4
|
718 |
+
spint==1.0.7
|
719 |
+
splot==1.1.5.post1
|
720 |
+
spopt==0.6.0
|
721 |
+
spreg==1.4.2
|
722 |
+
spvcm==0.3.0
|
723 |
+
sqlparse==0.4.4
|
724 |
+
squarify==0.4.3
|
725 |
+
srsly==2.4.8
|
726 |
+
stable-baselines3==2.1.0
|
727 |
+
stack-data==0.6.2
|
728 |
+
stack-data==0.6.3
|
729 |
+
stanio==0.5.0
|
730 |
+
starlette==0.32.0.post1
|
731 |
+
statsmodels==0.14.1
|
732 |
+
stemming==1.0.1
|
733 |
+
stop-words==2018.7.23
|
734 |
+
stopit==1.1.2
|
735 |
+
stumpy==1.12.0
|
736 |
+
sympy==1.12.1
|
737 |
+
tables==3.9.2
|
738 |
+
tabulate==0.9.0
|
739 |
+
tangled-up-in-unicode==0.2.0
|
740 |
+
tbb==2021.12.0
|
741 |
+
tblib==3.0.0
|
742 |
+
tenacity==8.2.3
|
743 |
+
tensorboard-data-server==0.7.2
|
744 |
+
tensorboard-plugin-profile==2.15.0
|
745 |
+
tensorboard==2.15.1
|
746 |
+
tensorboardX==2.6.2.2
|
747 |
+
tensorflow-cloud==0.1.16
|
748 |
+
tensorflow-datasets==4.9.4
|
749 |
+
tensorflow-decision-forests==1.8.1
|
750 |
+
tensorflow-estimator==2.15.0
|
751 |
+
tensorflow-hub==0.16.1
|
752 |
+
tensorflow-io-gcs-filesystem==0.35.0
|
753 |
+
tensorflow-io==0.35.0
|
754 |
+
tensorflow-metadata==0.14.0
|
755 |
+
tensorflow-probability==0.23.0
|
756 |
+
tensorflow-serving-api==2.14.1
|
757 |
+
tensorflow-text==2.15.0
|
758 |
+
tensorflow-transform==0.14.0
|
759 |
+
tensorflow==2.15.0
|
760 |
+
tensorstore==0.1.60
|
761 |
+
termcolor==2.4.0
|
762 |
+
terminado==0.18.0
|
763 |
+
testpath==0.6.0
|
764 |
+
text-unidecode==1.3
|
765 |
+
textblob==0.18.0.post0
|
766 |
+
texttable==1.7.0
|
767 |
+
tf_keras==2.15.1
|
768 |
+
tfp-nightly==0.24.0.dev0
|
769 |
+
thinc==8.2.3
|
770 |
+
threadpoolctl==3.2.0
|
771 |
+
tifffile==2023.12.9
|
772 |
+
timm==1.0.3
|
773 |
+
tinycss2==1.2.1
|
774 |
+
tobler==0.11.2
|
775 |
+
tokenizers==0.19.1
|
776 |
+
toml==0.10.2
|
777 |
+
tomli==2.0.1
|
778 |
+
tomlkit==0.12.5
|
779 |
+
toolz==0.12.1
|
780 |
+
torch==2.1.2
|
781 |
+
torchaudio==2.1.2
|
782 |
+
torchdata==0.7.1
|
783 |
+
torchinfo==1.8.0
|
784 |
+
torchmetrics==1.4.0.post0
|
785 |
+
torchtext==0.16.2
|
786 |
+
torchvision==0.16.2
|
787 |
+
tornado==6.3.3
|
788 |
+
tqdm==4.66.4
|
789 |
+
traceml==1.0.8
|
790 |
+
traitlets==5.9.0
|
791 |
+
traittypes==0.2.1
|
792 |
+
transformers==4.41.2
|
793 |
+
treelite==4.1.2
|
794 |
+
truststore==0.8.0
|
795 |
+
trx-python==0.2.9
|
796 |
+
tsfresh==0.20.2
|
797 |
+
typeguard==4.1.5
|
798 |
+
typer==0.9.0
|
799 |
+
typer==0.9.4
|
800 |
+
types-python-dateutil==2.8.19.20240106
|
801 |
+
typing-inspect==0.9.0
|
802 |
+
typing-utils==0.1.0
|
803 |
+
typing_extensions==4.9.0
|
804 |
+
tzdata==2023.4
|
805 |
+
tzdata==2024.1
|
806 |
+
uc-micro-py==1.0.3
|
807 |
+
ucx-py==0.37.0
|
808 |
+
ujson==5.10.0
|
809 |
+
umap-learn==0.5.6
|
810 |
+
unicodedata2==15.1.0
|
811 |
+
update-checker==0.18.0
|
812 |
+
uri-template==1.3.0
|
813 |
+
uritemplate==3.0.1
|
814 |
+
urllib3==1.26.18
|
815 |
+
urllib3==2.1.0
|
816 |
+
urwid==2.6.12
|
817 |
+
urwid_readline==0.14
|
818 |
+
uvicorn==0.25.0
|
819 |
+
uvloop==0.19.0
|
820 |
+
vaex-astro==0.9.3
|
821 |
+
vaex-core==4.17.1
|
822 |
+
vaex-hdf5==0.14.1
|
823 |
+
vaex-jupyter==0.8.2
|
824 |
+
vaex-ml==0.18.3
|
825 |
+
vaex-server==0.9.0
|
826 |
+
vaex-viz==0.5.4
|
827 |
+
vaex==4.17.0
|
828 |
+
vec_noise==1.1.4
|
829 |
+
vecstack==0.4.0
|
830 |
+
virtualenv==20.21.0
|
831 |
+
visions==0.7.5
|
832 |
+
vowpalwabbit==9.9.0
|
833 |
+
vtk==9.3.0
|
834 |
+
wandb==0.17.0
|
835 |
+
wasabi==1.1.2
|
836 |
+
watchfiles==0.21.0
|
837 |
+
wavio==0.0.9
|
838 |
+
wcwidth==0.2.13
|
839 |
+
weasel==0.3.4
|
840 |
+
webcolors==1.13
|
841 |
+
webencodings==0.5.1
|
842 |
+
websocket-client==1.7.0
|
843 |
+
websockets==12.0
|
844 |
+
wfdb==4.1.2
|
845 |
+
whatthepatch==1.0.5
|
846 |
+
wheel==0.42.0
|
847 |
+
widgetsnbextension==3.6.6
|
848 |
+
witwidget==1.8.1
|
849 |
+
woodwork==0.31.0
|
850 |
+
wordcloud==1.9.3
|
851 |
+
wordsegment==1.3.1
|
852 |
+
wrapt==1.14.1
|
853 |
+
xarray-einstats==0.7.0
|
854 |
+
xarray==2024.5.0
|
855 |
+
xgboost==2.0.3
|
856 |
+
xvfbwrapper==0.2.9
|
857 |
+
xxhash==3.4.1
|
858 |
+
xyzservices==2024.4.0
|
859 |
+
y-py==0.6.2
|
860 |
+
yapf==0.40.2
|
861 |
+
yarl==1.9.3
|
862 |
+
yarl==1.9.4
|
863 |
+
ydata-profiling==4.6.4
|
864 |
+
yellowbrick==1.5
|
865 |
+
ypy-websocket==0.8.4
|
866 |
+
zict==3.0.0
|
867 |
+
zipp==3.17.0
|
868 |
+
zstandard==0.19.0
|
wandb/run-20240704_045325-p1eykagd/files/wandb-metadata.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"os": "Linux-5.15.154+-x86_64-with-glibc2.31",
|
3 |
+
"python": "3.10.13",
|
4 |
+
"heartbeatAt": "2024-07-04T04:53:26.824325",
|
5 |
+
"startedAt": "2024-07-04T04:53:25.908057",
|
6 |
+
"docker": null,
|
7 |
+
"cuda": null,
|
8 |
+
"args": [],
|
9 |
+
"state": "running",
|
10 |
+
"program": "kaggle.ipynb",
|
11 |
+
"codePathLocal": null,
|
12 |
+
"root": "/kaggle/working",
|
13 |
+
"host": "9c8bb101f3ea",
|
14 |
+
"username": "root",
|
15 |
+
"executable": "/opt/conda/bin/python3.10",
|
16 |
+
"cpu_count": 2,
|
17 |
+
"cpu_count_logical": 4,
|
18 |
+
"cpu_freq": {
|
19 |
+
"current": 2000.15,
|
20 |
+
"min": 0.0,
|
21 |
+
"max": 0.0
|
22 |
+
},
|
23 |
+
"cpu_freq_per_core": [
|
24 |
+
{
|
25 |
+
"current": 2000.15,
|
26 |
+
"min": 0.0,
|
27 |
+
"max": 0.0
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"current": 2000.15,
|
31 |
+
"min": 0.0,
|
32 |
+
"max": 0.0
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"current": 2000.15,
|
36 |
+
"min": 0.0,
|
37 |
+
"max": 0.0
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"current": 2000.15,
|
41 |
+
"min": 0.0,
|
42 |
+
"max": 0.0
|
43 |
+
}
|
44 |
+
],
|
45 |
+
"disk": {
|
46 |
+
"/": {
|
47 |
+
"total": 8062.387607574463,
|
48 |
+
"used": 5689.501335144043
|
49 |
+
}
|
50 |
+
},
|
51 |
+
"gpu": "Tesla P100-PCIE-16GB",
|
52 |
+
"gpu_count": 1,
|
53 |
+
"gpu_devices": [
|
54 |
+
{
|
55 |
+
"name": "Tesla P100-PCIE-16GB",
|
56 |
+
"memory_total": 17179869184
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"memory": {
|
60 |
+
"total": 31.357574462890625
|
61 |
+
}
|
62 |
+
}
|
wandb/run-20240704_045325-p1eykagd/files/wandb-summary.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"train/loss": 0.9941, "train/grad_norm": 19.487234115600586, "train/learning_rate": 4.942965779467681e-07, "train/epoch": 3.0, "train/global_step": 6312, "_timestamp": 1720074701.425931, "_runtime": 5895.5103459358215, "_step": 15, "eval/loss": 1.1401793956756592, "eval/accuracy": 0.6116688319357506, "eval/runtime": 132.8, "eval/samples_per_second": 63.758, "eval/steps_per_second": 3.991, "train_runtime": 5918.3988, "train_samples_per_second": 17.061, "train_steps_per_second": 1.067, "total_flos": 2981042653335552.0, "train_loss": 1.2064072061400903}
|
wandb/run-20240704_045325-p1eykagd/logs/debug-internal.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|
wandb/run-20240704_045325-p1eykagd/logs/debug.log
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Current SDK version is 0.17.0
|
2 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Configure stats pid to 34
|
3 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
|
4 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
|
5 |
+
2024-07-04 04:53:25,909 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
|
6 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
|
7 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
|
8 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {}
|
9 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
|
10 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:_log_setup():520] Logging user logs to /kaggle/working/wandb/run-20240704_045325-p1eykagd/logs/debug.log
|
11 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:_log_setup():521] Logging internal logs to /kaggle/working/wandb/run-20240704_045325-p1eykagd/logs/debug-internal.log
|
12 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:_jupyter_setup():466] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7d849594c4c0>
|
13 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:init():560] calling init triggers
|
14 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
|
15 |
+
config: {}
|
16 |
+
2024-07-04 04:53:25,910 INFO MainThread:34 [wandb_init.py:init():610] starting backend
|
17 |
+
2024-07-04 04:53:25,911 INFO MainThread:34 [wandb_init.py:init():614] setting up manager
|
18 |
+
2024-07-04 04:53:25,912 INFO MainThread:34 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
|
19 |
+
2024-07-04 04:53:25,915 INFO MainThread:34 [wandb_init.py:init():622] backend started and connected
|
20 |
+
2024-07-04 04:53:25,928 INFO MainThread:34 [wandb_run.py:_label_probe_notebook():1328] probe notebook
|
21 |
+
2024-07-04 04:53:26,473 INFO MainThread:34 [wandb_init.py:init():711] updated telemetry
|
22 |
+
2024-07-04 04:53:26,476 INFO MainThread:34 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
|
23 |
+
2024-07-04 04:53:26,708 INFO MainThread:34 [wandb_run.py:_on_init():2396] communicating current version
|
24 |
+
2024-07-04 04:53:26,790 INFO MainThread:34 [wandb_run.py:_on_init():2405] got version response upgrade_message: "wandb version 0.17.4 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
|
25 |
+
|
26 |
+
2024-07-04 04:53:26,790 INFO MainThread:34 [wandb_init.py:init():795] starting run threads in backend
|
27 |
+
2024-07-04 04:53:42,841 INFO MainThread:34 [wandb_run.py:_console_start():2374] atexit reg
|
28 |
+
2024-07-04 04:53:42,841 INFO MainThread:34 [wandb_run.py:_redirect():2229] redirect: wrap_raw
|
29 |
+
2024-07-04 04:53:42,842 INFO MainThread:34 [wandb_run.py:_redirect():2294] Wrapping output streams.
|
30 |
+
2024-07-04 04:53:42,842 INFO MainThread:34 [wandb_run.py:_redirect():2319] Redirects installed.
|
31 |
+
2024-07-04 04:53:42,846 INFO MainThread:34 [wandb_init.py:init():838] run started, returning control to user process
|
32 |
+
2024-07-04 04:53:42,852 INFO MainThread:34 [wandb_run.py:_config_callback():1376] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BertForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8}, '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, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'cointegrated/rubert-tiny2', 'transformers_version': '4.41.2', 'emb_size': 312, 'gradient_checkpointing': False, 'model_type': 'bert', 'vocab_size': 83828, 'hidden_size': 312, 'num_hidden_layers': 3, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 600, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 2048, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_dir': '/kaggle/working/results', 'overwrite_output_dir': False, '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': 16, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 1e-05, 'weight_decay': 0.1, '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': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/logs', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'no', 'save_steps': 500, 'save_total_limit': None, '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, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/results', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'epoch', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False}
|
33 |
+
2024-07-04 06:31:41,429 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
34 |
+
2024-07-04 06:31:41,429 INFO MainThread:34 [wandb_init.py:_pause_backend():431] pausing backend
|
35 |
+
2024-07-04 06:38:44,273 INFO MainThread:34 [wandb_init.py:_resume_backend():436] resuming backend
|
wandb/run-20240704_045325-p1eykagd/run-p1eykagd.wandb
ADDED
Binary file (139 kB). View file
|
|