End of training

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: allenai/led-base-16384
+tags:
+- generated_from_trainer
+datasets:
+- scientific_papers
+model-index:
+- name: allenai/led-base-16384
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# allenai/led-base-16384
+
+This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the scientific_papers dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7667
+- Rouge2 Precision: 0.15
+- Rouge2 Recall: 0.0913
+- Rouge2 Fmeasure: 0.1075
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
+|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
+| 2.8931        | 0.32  | 10   | 2.9211          | 0.1243           | 0.1206        | 0.1119          |
+| 3.0026        | 0.64  | 20   | 2.8150          | 0.1589           | 0.1102        | 0.1241          |
+| 2.7651        | 0.96  | 30   | 2.7667          | 0.15             | 0.0913        | 0.1075          |
+
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "allenai/led-base-16384",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 512,
+  "min_length": 100,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "use_cache": false,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 100,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978f714b3326fbac498c33a12ec115bb29d11415bbfa7bbdf7cb5d0330060790
+size 647614116

runs/Jan03_10-55-16_416a3b7a3d3d/events.out.tfevents.1704279323.416a3b7a3d3d.99.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f31c738e5789918a849fd88445c34dfc3022bed19f25ade8845eeaca402d702
+size 5384

runs/Jan03_11-05-09_416a3b7a3d3d/events.out.tfevents.1704279912.416a3b7a3d3d.99.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4b594ec94e061283c1279b8eff5f16fd6ffb592bef52e20e1060b45f4ac1a5
+size 7665

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8bbd6b5a6dc612ef1cf9874c87292958457840d40ca01939f9dae1c60bf486
+size 4347

wandb/debug.log

@@ -0,0 +1,55 @@
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Configure stats pid to 99
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_init.py:_log_setup():524] Logging user logs to /kaggle/working/wandb/run-20240103_105541-kk0m5fl8/logs/debug.log
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_init.py:_log_setup():525] Logging internal logs to /kaggle/working/wandb/run-20240103_105541-kk0m5fl8/logs/debug-internal.log
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x78c0792cf100>
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():564] calling init triggers
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+config: {}
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():614] starting backend
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():618] setting up manager
+2024-01-03 10:55:41,498 INFO    MainThread:99 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-01-03 10:55:41,501 INFO    MainThread:99 [wandb_init.py:init():624] backend started and connected
+2024-01-03 10:55:41,513 INFO    MainThread:99 [wandb_run.py:_label_probe_notebook():1294] probe notebook
+2024-01-03 10:55:42,150 INFO    MainThread:99 [wandb_init.py:init():716] updated telemetry
+2024-01-03 10:55:42,164 INFO    MainThread:99 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2024-01-03 10:55:42,671 INFO    MainThread:99 [wandb_run.py:_on_init():2254] communicating current version
+2024-01-03 10:55:42,725 INFO    MainThread:99 [wandb_run.py:_on_init():2263] got version response 
+2024-01-03 10:55:42,725 INFO    MainThread:99 [wandb_init.py:init():800] starting run threads in backend
+2024-01-03 10:56:12,751 INFO    MainThread:99 [wandb_run.py:_console_start():2233] atexit reg
+2024-01-03 10:56:12,751 INFO    MainThread:99 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2024-01-03 10:56:12,752 INFO    MainThread:99 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2024-01-03 10:56:12,752 INFO    MainThread:99 [wandb_run.py:_redirect():2178] Redirects installed.
+2024-01-03 10:56:12,753 INFO    MainThread:99 [wandb_init.py:init():841] run started, returning control to user process
+2024-01-03 10:56:12,760 INFO    MainThread:99 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 50265, 'max_encoder_position_embeddings': 16384, 'max_decoder_position_embeddings': 1024, 'd_model': 768, 'encoder_ffn_dim': 3072, 'encoder_layers': 6, 'encoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'decoder_layers': 6, 'decoder_attention_heads': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': False, 'num_hidden_layers': 6, 'attention_window': [1024, 1024, 1024, 1024, 1024, 1024], 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 512, 'min_length': 100, 'do_sample': False, 'early_stopping': True, 'num_beams': 2, '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': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LEDForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'allenai/led-base-16384', 'transformers_version': '4.36.0', 'classif_dropout': 0.0, 'model_type': 'led', 'output_dir': './', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, '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': './runs/Jan03_10-55-16_416a3b7a3d3d', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, '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': 10, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': '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': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None}
+2024-01-03 11:04:25,631 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:04:25,631 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:08,175 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:08,177 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:08,177 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:09,557 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:09,559 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:09,559 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:09,778 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:09,785 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:09,785 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:11,278 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:11,290 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:11,290 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:12,067 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:12,538 INFO    MainThread:99 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 50265, 'max_encoder_position_embeddings': 16384, 'max_decoder_position_embeddings': 1024, 'd_model': 768, 'encoder_ffn_dim': 3072, 'encoder_layers': 6, 'encoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'decoder_layers': 6, 'decoder_attention_heads': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': False, 'num_hidden_layers': 6, 'attention_window': [1024, 1024, 1024, 1024, 1024, 1024], 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 512, 'min_length': 100, 'do_sample': False, 'early_stopping': True, 'num_beams': 2, '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': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LEDForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'allenai/led-base-16384', 'transformers_version': '4.36.0', 'classif_dropout': 0.0, 'model_type': 'led', 'output_dir': './', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, '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': './runs/Jan03_11-05-09_416a3b7a3d3d', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, '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': 10, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': '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': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None}
+2024-01-03 11:27:53,766 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:27:53,766 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:28:23,468 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:28:24,109 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:28:24,109 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:29:06,752 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:29:06,779 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:29:06,780 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:29:56,569 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend

wandb/run-20240103_105541-kk0m5fl8/files/conda-environment.yaml

@@ -0,0 +1,1060 @@
+name: base
+channels:
+  - pytorch
+  - file:///tmp/conda
+  - rapidsai
+  - nvidia
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - aiohttp=3.8.5=py310h2372a71_0
+  - aiosignal=1.3.1=pyhd8ed1ab_0
+  - annotated-types=0.6.0=pyhd8ed1ab_0
+  - anyio=3.7.1=pyhd8ed1ab_0
+  - archspec=0.2.2=pyhd8ed1ab_0
+  - argon2-cffi-bindings=21.2.0=py310h5764c6d_3
+  - arrow=1.2.3=pyhd8ed1ab_0
+  - arrow-cpp=11.0.0=ha770c72_9_cpu
+  - asttokens=2.2.1=pyhd8ed1ab_0
+  - async-lru=2.0.4=pyhd8ed1ab_0
+  - async-timeout=4.0.3=pyhd8ed1ab_0
+  - atk-1.0=2.38.0=hd4edc92_1
+  - attrs=23.1.0=pyh71513ae_1
+  - aws-c-auth=0.6.26=h987a71b_2
+  - aws-c-cal=0.5.21=h48707d8_2
+  - aws-c-common=0.8.14=h0b41bf4_0
+  - aws-c-compression=0.2.16=h03acc5a_5
+  - aws-c-event-stream=0.2.20=h00877a2_4
+  - aws-c-http=0.7.6=hf342b9f_0
+  - aws-c-io=0.13.19=h5b20300_3
+  - aws-c-mqtt=0.8.6=hc4349f7_12
+  - aws-c-s3=0.2.7=h909e904_1
+  - aws-c-sdkutils=0.1.9=h03acc5a_0
+  - aws-checksums=0.1.14=h03acc5a_5
+  - aws-crt-cpp=0.19.8=hf7fbfca_12
+  - aws-sdk-cpp=1.10.57=h17c43bd_8
+  - babel=2.12.1=pyhd8ed1ab_1
+  - backcall=0.2.0=pyh9f0ad1d_0
+  - backports=1.0=pyhd8ed1ab_3
+  - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
+  - beautifulsoup4=4.12.2=pyha770c72_0
+  - bleach=6.0.0=pyhd8ed1ab_0
+  - bokeh=3.3.2=pyhd8ed1ab_0
+  - boltons=23.0.0=pyhd8ed1ab_0
+  - brotli=1.0.9=h166bdaf_9
+  - brotli-bin=1.0.9=h166bdaf_9
+  - brotlipy=0.7.0=py310h7f8727e_1002
+  - bzip2=1.0.8=h7b6447c_0
+  - c-ares=1.23.0=hd590300_0
+  - ca-certificates=2023.11.17=hbcca054_0
+  - cached-property=1.5.2=hd8ed1ab_1
+  - cached_property=1.5.2=pyha770c72_1
+  - cairo=1.18.0=h3faef2a_0
+  - cartopy=0.22.0=py310hcc13569_1
+  - catalogue=2.0.10=py310hff52083_0
+  - certifi=2023.11.17=pyhd8ed1ab_0
+  - cffi=1.15.1=py310h255011f_3
+  - charset-normalizer=3.2.0=pyhd8ed1ab_0
+  - click=8.1.7=unix_pyh707e725_0
+  - cloudpathlib=0.16.0=pyhd8ed1ab_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - comm=0.1.4=pyhd8ed1ab_0
+  - conda=23.7.4=py310hff52083_0
+  - conda-libmamba-solver=23.7.0=pyhd8ed1ab_0
+  - conda-package-handling=2.2.0=pyh38be061_0
+  - conda-package-streaming=0.9.0=pyhd8ed1ab_0
+  - confection=0.1.4=py310h17c5347_0
+  - cryptography=41.0.3=py310h75e40e8_0
+  - cubinlinker=0.3.0=py310hfdf336d_0
+  - cuda-cudart=11.8.89=0
+  - cuda-nvrtc=11.8.89=0
+  - cuda-profiler-api=11.8.86=0
+  - cuda-python=11.8.3=py310hf9913ef_0
+  - cuda-version=11.8=h70ddcb2_2
+  - cudatoolkit=11.8.0=h4ba93d1_12
+  - cudf=23.08.00=cuda11_py310_230809_g8150d38e08_0
+  - cuml=23.08.00=cuda11_py310_230809_gd7162cdea_0
+  - cupy=12.3.0=py310hf4db66c_0
+  - curl=8.5.0=hca28451_0
+  - cymem=2.0.8=py310hc6cd4ac_1
+  - cython-blis=0.7.10=py310h1f7b6fc_2
+  - cytoolz=0.12.2=py310h2372a71_1
+  - dask-cuda=23.08.00=py310_230809_gefbd6ca_0
+  - dask-cudf=23.08.00=cuda11_py310_230809_g8150d38e08_0
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - defusedxml=0.7.1=pyhd8ed1ab_0
+  - distro=1.8.0=pyhd8ed1ab_0
+  - dlenv-tf-2-13-gpu=1.0.20230823=py310had803b4_0
+  - dlpack=0.5=h9c3ff4c_0
+  - entrypoints=0.4=pyhd8ed1ab_0
+  - exceptiongroup=1.1.3=pyhd8ed1ab_0
+  - executing=1.2.0=pyhd8ed1ab_0
+  - expat=2.5.0=hcb278e6_1
+  - fastrlock=0.8.2=py310hc6cd4ac_1
+  - fftw=3.3.10=nompi_hc118613_108
+  - flit-core=3.9.0=pyhd8ed1ab_0
+  - fmt=9.1.0=h924138e_0
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=h77eed37_1
+  - fontconfig=2.14.2=h14ed4e7_0
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - fqdn=1.5.1=pyhd8ed1ab_0
+  - freetype=2.12.1=h267a509_2
+  - fribidi=1.0.10=h36c2ea0_0
+  - frozenlist=1.4.0=py310h2372a71_0
+  - gdk-pixbuf=2.42.10=h829c605_4
+  - geos=3.11.1=h27087fc_0
+  - gettext=0.21.1=h27087fc_0
+  - gflags=2.2.2=he1b5a44_1004
+  - ghostscript=10.02.1=h59595ed_0
+  - giflib=5.2.1=h0b41bf4_3
+  - glog=0.6.0=h6f12383_0
+  - gmock=1.14.0=ha770c72_1
+  - google-api-core-grpc=2.11.1=hd8ed1ab_0
+  - google-auth=2.22.0=pyh1a96a4e_0
+  - google-cloud-core=2.3.3=pyhd8ed1ab_0
+  - google-cloud-datastore=2.18.0=pyhd8ed1ab_0
+  - googleapis-common-protos=1.60.0=pyhd8ed1ab_0
+  - graphite2=1.3.13=h58526e2_1001
+  - graphviz=9.0.0=h78e8752_1
+  - grpc-cpp=1.51.1=h27aab58_3
+  - gtest=1.14.0=h00ab1b0_1
+  - gtk2=2.24.33=h7f000aa_3
+  - gts=0.7.6=h977cf35_4
+  - harfbuzz=8.3.0=h3d44ed6_0
+  - icu=73.2=h59595ed_0
+  - idna=3.4=pyhd8ed1ab_0
+  - imagemagick=7.1.1_21=pl5321hdc43972_1
+  - importlib-metadata=6.8.0=pyha770c72_0
+  - importlib_metadata=6.8.0=hd8ed1ab_0
+  - importlib_resources=6.0.1=pyhd8ed1ab_0
+  - intel-openmp=2023.1.0=hdb19cb5_46306
+  - ipykernel=6.25.1=pyh71e2992_0
+  - ipython=8.14.0=pyh41d4057_0
+  - isoduration=20.11.0=pyhd8ed1ab_0
+  - jbig=2.1=h7f98852_2003
+  - jedi=0.19.0=pyhd8ed1ab_0
+  - jinja2=3.1.2=pyhd8ed1ab_1
+  - joblib=1.3.2=pyhd8ed1ab_0
+  - json5=0.9.14=pyhd8ed1ab_0
+  - jsonpatch=1.32=pyhd8ed1ab_0
+  - jsonpointer=2.0=py_0
+  - jsonschema=4.19.0=pyhd8ed1ab_1
+  - jsonschema-specifications=2023.7.1=pyhd8ed1ab_0
+  - jsonschema-with-format-nongpl=4.19.0=pyhd8ed1ab_1
+  - jupyter_client=8.3.0=pyhd8ed1ab_0
+  - jupyter_core=5.3.1=py310hff52083_0
+  - jupyter_server=2.7.1=pyhd8ed1ab_0
+  - jupyter_server_terminals=0.4.4=pyhd8ed1ab_1
+  - jupyterlab_pygments=0.2.2=pyhd8ed1ab_0
+  - jupyterlab_server=2.24.0=pyhd8ed1ab_0
+  - keyutils=1.6.1=h166bdaf_0
+  - krb5=1.21.2=h659d440_0
+  - langcodes=3.3.0=pyhd8ed1ab_0
+  - lcms2=2.16=hb7c19ff_0
+  - ld_impl_linux-64=2.40=h41732ed_0
+  - lerc=4.0.0=h27087fc_0
+  - libabseil=20230125.0=cxx17_hcb278e6_1
+  - libarchive=3.6.2=h039dbb9_1
+  - libarrow=11.0.0=h33598ff_9_cpu
+  - libblas=3.9.0=20_linux64_openblas
+  - libbrotlicommon=1.0.9=h166bdaf_9
+  - libbrotlidec=1.0.9=h166bdaf_9
+  - libbrotlienc=1.0.9=h166bdaf_9
+  - libcblas=3.9.0=20_linux64_openblas
+  - libcrc32c=1.1.2=h9c3ff4c_0
+  - libcublas=11.11.3.6=0
+  - libcublas-dev=11.11.3.6=0
+  - libcudf=23.08.00=cuda11_230809_g8150d38e08_0
+  - libcufft=10.9.0.58=0
+  - libcufile=1.4.0.31=0
+  - libcufile-dev=1.4.0.31=0
+  - libcuml=23.08.00=cuda11_230809_gd7162cdea_0
+  - libcumlprims=23.08.00=cuda11_230809_g71c0a86_0
+  - libcurand=10.3.0.86=0
+  - libcurand-dev=10.3.0.86=0
+  - libcurl=8.5.0=hca28451_0
+  - libcusolver=11.4.1.48=0
+  - libcusolver-dev=11.4.1.48=0
+  - libcusparse=11.7.5.86=0
+  - libcusparse-dev=11.7.5.86=0
+  - libdeflate=1.19=hd590300_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libev=4.33=hd590300_2
+  - libevent=2.1.10=h28343ad_4
+  - libexpat=2.5.0=hcb278e6_1
+  - libffi=3.4.2=h7f98852_5
+  - libgcc=7.2.0=h69d50b8_2
+  - libgcc-ng=13.1.0=he5830b7_0
+  - libgd=2.3.3=h119a65a_9
+  - libgfortran-ng=13.2.0=h69a702a_0
+  - libgfortran5=13.2.0=ha4646dd_0
+  - libglib=2.78.3=h783c2da_0
+  - libgomp=13.1.0=he5830b7_0
+  - libgoogle-cloud=2.8.0=h3c06191_0
+  - libgrpc=1.51.1=hcf146ea_3
+  - libiconv=1.17=hd590300_1
+  - libjpeg-turbo=3.0.0=hd590300_1
+  - libkvikio=23.08.00=cuda11_230809_g51a9036_0
+  - liblapack=3.9.0=20_linux64_openblas
+  - libllvm14=14.0.6=hcd5def8_4
+  - libmamba=1.5.0=h658169a_0
+  - libmambapy=1.5.0=py310h8aae740_0
+  - libnghttp2=1.58.0=h47da74e_1
+  - libnsl=2.0.0=h7f98852_0
+  - libnuma=2.0.16=h0b41bf4_1
+  - libopenblas=0.3.25=pthreads_h413a1c8_0
+  - libpng=1.6.39=h753d276_0
+  - libprotobuf=3.21.12=hfc55251_2
+  - libraft=23.08.00=cuda11_230809_ge588d7b5_0
+  - libraft-headers=23.08.00=cuda11_230809_ge588d7b5_0
+  - libraft-headers-only=23.08.00=cuda11_230809_ge588d7b5_0
+  - librmm=23.08.00=cuda11_230809_gf3af0e8d_0
+  - librsvg=2.56.3=h98fae49_0
+  - libsodium=1.0.18=h36c2ea0_1
+  - libsolv=0.7.27=hfc55251_0
+  - libsqlite=3.44.2=h2797004_0
+  - libssh2=1.11.0=h0841786_0
+  - libstdcxx-ng=13.1.0=hfd8a6a1_0
+  - libthrift=0.18.0=h5e4af38_0
+  - libtiff=4.6.0=ha9c0a0a_2
+  - libutf8proc=2.8.0=h166bdaf_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libuv=1.44.2=hd590300_1
+  - libwebp=1.3.2=h658648e_1
+  - libwebp-base=1.3.2=hd590300_0
+  - libxcb=1.15=h0b41bf4_0
+  - libxml2=2.11.6=h232c23b_0
+  - libzlib=1.2.13=hd590300_5
+  - llvm-openmp=8.0.1=hc9558a2_0
+  - locket=1.0.0=pyhd8ed1ab_0
+  - lz4=4.3.2=py310h350c4a5_1
+  - lz4-c=1.9.4=hcb278e6_0
+  - lzo=2.10=h516909a_1000
+  - magma-cuda118=2.6.1=1
+  - mamba=1.5.0=py310h51d5547_0
+  - markdown-it-py=3.0.0=pyhd8ed1ab_0
+  - markupsafe=2.1.3=py310h2372a71_0
+  - matplotlib-base=3.8.2=py310h62c0568_0
+  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
+  - menuinst=2.0.1=py310hff52083_0
+  - mkl=2023.1.0=h213fc3f_46344
+  - msgpack-python=1.0.7=py310hd41b1e2_0
+  - multidict=6.0.4=py310h1fa729e_0
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - murmurhash=1.0.10=py310hc6cd4ac_1
+  - nb_conda=2.2.1=unix_6
+  - nb_conda_kernels=2.3.1=py310hff52083_2
+  - nbformat=5.9.2=pyhd8ed1ab_0
+  - nccl=2.19.4.1=h6103f9b_0
+  - ncurses=6.4=hcb278e6_0
+  - nodejs=6.13.1=0
+  - notebook-shim=0.2.3=pyhd8ed1ab_0
+  - nvcomp=2.6.1=h838ba91_3
+  - nvtx=0.2.8=py310h2372a71_1
+  - openjpeg=2.5.0=h488ebb8_3
+  - openmp=8.0.1=0
+  - openssl=3.2.0=hd590300_1
+  - orc=1.8.2=hfdbbad2_2
+  - pandocfilters=1.5.0=pyhd8ed1ab_0
+  - pango=1.50.14=ha41ecd1_2
+  - parquet-cpp=1.5.1=2
+  - parso=0.8.3=pyhd8ed1ab_0
+  - partd=1.4.1=pyhd8ed1ab_0
+  - pathy=0.10.1=py310h06a4308_0
+  - pcre2=10.42=hcad00b1_0
+  - perl=5.32.1=4_hd590300_perl5
+  - pexpect=4.8.0=pyh1a96a4e_2
+  - pickleshare=0.7.5=py_1003
+  - pip=23.2.1=pyhd8ed1ab_0
+  - pixman=0.42.2=h59595ed_0
+  - pkg-config=0.29.2=h36c2ea0_1008
+  - pkgutil-resolve-name=1.3.10=pyhd8ed1ab_0
+  - pluggy=1.2.0=pyhd8ed1ab_0
+  - preshed=3.0.9=py310hc6cd4ac_1
+  - proj=9.3.1=h1d62c97_0
+  - prometheus_client=0.17.1=pyhd8ed1ab_0
+  - prompt-toolkit=3.0.39=pyha770c72_0
+  - prompt_toolkit=3.0.39=hd8ed1ab_0
+  - pthread-stubs=0.4=h36c2ea0_1001
+  - ptxcompiler=0.8.1=py310h70a93da_2
+  - ptyprocess=0.7.0=pyhd3deb0d_0
+  - pure_eval=0.2.2=pyhd8ed1ab_0
+  - pyarrow=11.0.0=py310h633f555_9_cpu
+  - pybind11-abi=4=hd8ed1ab_3
+  - pycosat=0.6.4=py310h5764c6d_1
+  - pydantic-core=2.14.5=py310hcb5633a_0
+  - pygments=2.16.1=pyhd8ed1ab_0
+  - pylibraft=23.08.00=cuda11_py310_230809_ge588d7b5_0
+  - pynvml=11.4.1=pyhd8ed1ab_0
+  - pyopenssl=23.2.0=pyhd8ed1ab_1
+  - pyproj=3.6.1=py310hd5c30f3_5
+  - pyshp=2.3.1=pyhd8ed1ab_0
+  - pysocks=1.7.1=py310h06a4308_0
+  - python=3.10.12=hd12c33a_0_cpython
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python-fastjsonschema=2.18.0=pyhd8ed1ab_0
+  - python-json-logger=2.0.7=pyhd8ed1ab_0
+  - python_abi=3.10=3_cp310
+  - pytz=2023.3=pyhd8ed1ab_0
+  - pyu2f=0.1.5=pyhd8ed1ab_0
+  - pyyaml=6.0.1=py310h2372a71_0
+  - raft-dask=23.08.00=cuda11_py310_230809_ge588d7b5_0
+  - rdma-core=28.9=h59595ed_1
+  - re2=2023.02.02=hcb278e6_0
+  - readline=8.2=h8228510_1
+  - referencing=0.30.2=pyhd8ed1ab_0
+  - reproc=14.2.4.post0=hd590300_1
+  - reproc-cpp=14.2.4.post0=h59595ed_1
+  - requests=2.31.0=pyhd8ed1ab_0
+  - rfc3339-validator=0.1.4=pyhd8ed1ab_0
+  - rfc3986-validator=0.1.1=pyh9f0ad1d_0
+  - rmm=23.08.00=cuda11_py310_230809_gf3af0e8d_0
+  - rpds-py=0.9.2=py310hcb5633a_0
+  - rsa=4.9=pyhd8ed1ab_0
+  - ruamel.yaml=0.17.32=py310h2372a71_0
+  - ruamel.yaml.clib=0.2.7=py310h1fa729e_1
+  - ruamel_yaml=0.15.100=py310h7f8727e_0
+  - s2n=1.3.41=h3358134_0
+  - send2trash=1.8.2=pyh41d4057_0
+  - setuptools=68.1.2=pyhd8ed1ab_0
+  - shapely=1.8.5=py310h5b266fc_2
+  - shellingham=1.5.4=pyhd8ed1ab_0
+  - smart_open=6.4.0=pyhd8ed1ab_0
+  - snappy=1.1.10=h9fff704_0
+  - sniffio=1.3.0=pyhd8ed1ab_0
+  - sortedcontainers=2.4.0=pyhd8ed1ab_0
+  - spacy=3.7.2=py310hcb52e73_0
+  - spacy-legacy=3.0.12=pyhd8ed1ab_0
+  - spacy-loggers=1.0.5=pyhd8ed1ab_0
+  - spdlog=1.11.0=h9b3ece8_1
+  - sqlite=3.38.2=hc218d9a_0
+  - srsly=2.4.8=py310hc6cd4ac_1
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - tblib=3.0.0=pyhd8ed1ab_0
+  - terminado=0.17.1=pyh41d4057_0
+  - thinc=8.2.1=py310hcb52e73_0
+  - tinycss2=1.2.1=pyhd8ed1ab_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - tomli=2.0.1=pyhd8ed1ab_0
+  - toolz=0.12.0=pyhd8ed1ab_0
+  - tornado=6.3.3=py310h2372a71_0
+  - tqdm=4.66.1=pyhd8ed1ab_0
+  - traitlets=5.9.0=pyhd8ed1ab_0
+  - treelite=3.2.0=py310h1be96d9_0
+  - truststore=0.8.0=pyhd8ed1ab_0
+  - typer=0.9.0=pyhd8ed1ab_0
+  - typing_extensions=4.7.1=pyha770c72_0
+  - typing_utils=0.1.0=pyhd8ed1ab_0
+  - ucx=1.14.1=h64cca9d_5
+  - ucx-proc=1.0.0=gpu
+  - ucx-py=0.33.00=py310_230809_gea1eb8f_0
+  - unicodedata2=15.1.0=py310h2372a71_0
+  - uri-template=1.3.0=pyhd8ed1ab_0
+  - wasabi=1.1.2=py310hff52083_0
+  - wcwidth=0.2.6=pyhd8ed1ab_0
+  - weasel=0.3.4=pyhd8ed1ab_0
+  - webcolors=1.13=pyhd8ed1ab_0
+  - websocket-client=1.6.2=pyhd8ed1ab_0
+  - wheel=0.41.2=pyhd8ed1ab_0
+  - xorg-kbproto=1.0.7=h7f98852_1002
+  - xorg-libice=1.1.1=hd590300_0
+  - xorg-libsm=1.2.4=h7391055_0
+  - xorg-libx11=1.8.7=h8ee46fc_0
+  - xorg-libxau=1.0.11=hd590300_0
+  - xorg-libxdmcp=1.1.3=h7f98852_0
+  - xorg-libxext=1.3.4=h0b41bf4_2
+  - xorg-libxrender=0.9.11=hd590300_0
+  - xorg-libxt=1.3.0=hd590300_1
+  - xorg-renderproto=0.11.1=h7f98852_1002
+  - xorg-xextproto=7.3.0=h0b41bf4_1003
+  - xorg-xproto=7.0.31=h7f98852_1007
+  - xyzservices=2023.10.1=pyhd8ed1ab_0
+  - xz=5.2.6=h166bdaf_0
+  - yaml=0.2.5=h7b6447c_0
+  - yaml-cpp=0.7.0=h59595ed_3
+  - yarl=1.9.2=py310h2372a71_0
+  - zeromq=4.3.4=h9c3ff4c_1
+  - zict=3.0.0=pyhd8ed1ab_0
+  - zipp=3.16.2=pyhd8ed1ab_0
+  - zlib=1.2.13=hd590300_5
+  - zstandard=0.22.0=py310h1275a96_0
+  - zstd=1.5.5=hfc55251_0
+  - pip:
+      - absl-py==1.4.0
+      - accelerate==0.25.0
+      - access==1.1.9
+      - affine==2.4.0
+      - aiobotocore==2.8.0
+      - aiohttp-cors==0.7.0
+      - aioitertools==0.11.0
+      - aiorwlock==1.3.0
+      - albumentations==1.3.1
+      - alembic==1.13.0
+      - altair==5.2.0
+      - annoy==1.17.3
+      - ansiwrap==0.8.4
+      - apache-beam==2.46.0
+      - aplus==0.11.0
+      - appdirs==1.4.4
+      - argon2-cffi==23.1.0
+      - array-record==0.4.1
+      - arviz==0.12.1
+      - astroid==3.0.2
+      - astropy==6.0.0
+      - astropy-iers-data==0.2023.12.11.0.31.11
+      - astunparse==1.6.3
+      - audioread==3.0.1
+      - autopep8==2.0.4
+      - backoff==2.2.1
+      - bayesian-optimization==1.4.3
+      - bayespy==0.5.26
+      - beatrix-jupyterlab==2023.814.150030
+      - bidict==0.22.1
+      - biopython==1.81
+      - blake3==0.2.1
+      - blessed==1.20.0
+      - blinker==1.7.0
+      - blosc2==2.3.2
+      - boruta==0.3
+      - boto3==1.26.100
+      - botocore==1.33.1
+      - bqplot==0.12.42
+      - branca==0.7.0
+      - brewer2mpl==1.4.1
+      - cachetools==4.2.4
+      - catalyst==22.4
+      - catboost==1.2.2
+      - category-encoders==2.6.3
+      - cesium==0.12.1
+      - cftime==1.6.3
+      - chex==0.1.85
+      - cleverhans==4.0.0
+      - click-plugins==1.1.1
+      - cligj==0.7.2
+      - cloud-tpu-client==0.10
+      - cloud-tpu-profiler==2.4.0
+      - cloudpickle==2.2.1
+      - cmdstanpy==1.2.0
+      - cmudict==1.0.15
+      - colorcet==3.0.1
+      - colorful==0.5.5
+      - colorlog==6.8.0
+      - colorlover==0.3.0
+      - contextily==1.4.0
+      - contourpy==1.1.0
+      - convertdate==2.4.0
+      - crcmod==1.7
+      - cubinlinker-cu11==0.3.0.post1
+      - cufflinks==0.17.3
+      - cvxcanon==0.1.2
+      - cycler==0.11.0
+      - cysignals==1.11.4
+      - cython==3.0.0
+      - daal==2024.0.1
+      - daal4py==2024.0.1
+      - dacite==1.8.1
+      - dask==2023.12.0
+      - dataclasses-json==0.6.3
+      - datasets==2.1.0
+      - datashader==0.16.0
+      - datatile==1.0.3
+      - db-dtypes==1.1.1
+      - deap==1.4.1
+      - debugpy==1.6.7.post1
+      - delorean==1.0.0
+      - deprecat==2.1.1
+      - deprecated==1.2.14
+      - deprecation==2.1.0
+      - descartes==1.1.0
+      - dill==0.3.7
+      - dipy==1.7.0
+      - distlib==0.3.7
+      - distributed==2023.12.0
+      - dm-tree==0.1.8
+      - docker==6.1.3
+      - docker-pycreds==0.4.0
+      - docopt==0.6.2
+      - docstring-parser==0.15
+      - docstring-to-markdown==0.13
+      - docutils==0.20.1
+      - earthengine-api==0.1.383
+      - easydict==1.11
+      - easyocr==1.7.1
+      - ecos==2.0.12
+      - eli5==0.13.0
+      - emoji==2.9.0
+      - en-core-web-lg==3.7.1
+      - en-core-web-sm==3.7.1
+      - ephem==4.1.5
+      - esda==2.5.1
+      - essentia==2.1b6.dev1110
+      - et-xmlfile==1.1.0
+      - etils==1.4.1
+      - explainable-ai-sdk==1.3.3
+      - farama-notifications==0.0.4
+      - fastai==2.7.13
+      - fastapi==0.101.1
+      - fastavro==1.8.2
+      - fastcore==1.5.29
+      - fastdownload==0.0.7
+      - fasteners==0.18
+      - fastprogress==1.0.3
+      - fasttext==0.9.2
+      - fbpca==1.0
+      - feather-format==0.4.1
+      - featuretools==1.28.0
+      - filelock==3.12.2
+      - fiona==1.9.5
+      - fitter==1.6.0
+      - flake8==6.1.0
+      - flashtext==2.7
+      - flask==3.0.0
+      - flatbuffers==23.5.26
+      - flax==0.7.5
+      - folium==0.15.1
+      - fonttools==4.42.1
+      - frozendict==2.3.10
+      - fsspec==2023.6.0
+      - funcy==2.0
+      - fury==0.9.0
+      - future==0.18.3
+      - fuzzywuzzy==0.18.0
+      - gast==0.4.0
+      - gatspy==0.3
+      - gcsfs==2023.6.0
+      - gensim==4.3.2
+      - geographiclib==2.0
+      - geohash==1.0
+      - geojson==3.1.0
+      - geopandas==0.14.1
+      - geoplot==0.5.1
+      - geopy==2.4.1
+      - geoviews==1.11.0
+      - ggplot==0.11.5
+      - giddy==2.3.4
+      - gitdb==4.0.10
+      - gitpython==3.1.32
+      - google-ai-generativelanguage==0.4.0
+      - google-api-core==2.15.0
+      - google-api-python-client==2.111.0
+      - google-apitools==0.5.31
+      - google-auth-httplib2==0.1.0
+      - google-auth-oauthlib==1.0.0
+      - google-cloud-aiplatform==0.6.0a1
+      - google-cloud-artifact-registry==1.8.3
+      - google-cloud-automl==1.0.1
+      - google-cloud-bigquery==2.34.4
+      - google-cloud-bigtable==1.7.3
+      - google-cloud-dlp==3.12.2
+      - google-cloud-language==2.12.0
+      - google-cloud-monitoring==2.15.1
+      - google-cloud-pubsub==2.18.3
+      - google-cloud-pubsublite==1.8.3
+      - google-cloud-recommendations-ai==0.7.1
+      - google-cloud-resource-manager==1.10.3
+      - google-cloud-spanner==3.40.1
+      - google-cloud-storage==1.44.0
+      - google-cloud-translate==3.12.1
+      - google-cloud-videointelligence==2.12.0
+      - google-cloud-vision==2.8.0
+      - google-crc32c==1.5.0
+      - google-generativeai==0.3.0
+      - google-pasta==0.2.0
+      - google-resumable-media==2.5.0
+      - gplearn==0.4.2
+      - gpustat==1.0.0
+      - gpxpy==1.6.2
+      - greenlet==2.0.2
+      - grpc-google-iam-v1==0.12.6
+      - grpcio==1.57.0
+      - grpcio-status==1.48.2
+      - gviz-api==1.10.0
+      - gym==0.26.2
+      - gym-notices==0.0.8
+      - gymnasium==0.29.0
+      - gymnasium-notices==0.0.1
+      - h11==0.14.0
+      - h2o==3.44.0.2
+      - h5py==3.9.0
+      - haversine==2.8.0
+      - hdfs==2.7.2
+      - hep-ml==0.7.2
+      - hijri-converter==2.3.1
+      - hmmlearn==0.3.0
+      - holidays==0.24
+      - holoviews==1.18.1
+      - hpsklearn==0.1.0
+      - html5lib==1.1
+      - htmlmin==0.1.12
+      - httplib2==0.21.0
+      - httptools==0.6.1
+      - huggingface-hub==0.19.4
+      - humanize==4.9.0
+      - hunspell==0.5.5
+      - husl==4.0.3
+      - hydra-slayer==0.4.1
+      - hyperopt==0.2.7
+      - hypertools==0.8.0
+      - igraph==0.11.3
+      - imagecodecs==2023.9.18
+      - imagehash==4.3.1
+      - imageio==2.31.1
+      - imbalanced-learn==0.11.0
+      - imgaug==0.4.0
+      - importlib-resources==5.13.0
+      - inequality==1.0.1
+      - iniconfig==2.0.0
+      - ipydatawidgets==4.3.5
+      - ipyleaflet==0.18.0
+      - ipympl==0.7.0
+      - ipython-genutils==0.2.0
+      - ipython-sql==0.5.0
+      - ipyvolume==0.6.3
+      - ipyvue==1.10.1
+      - ipyvuetify==1.8.10
+      - ipywebrtc==0.6.0
+      - ipywidgets==7.7.1
+      - isort==5.13.1
+      - isoweek==1.3.3
+      - itsdangerous==2.1.2
+      - janome==0.5.0
+      - jaraco-classes==3.3.0
+      - jax==0.4.21
+      - jaxlib==0.4.21+cuda11.cudnn86
+      - jeepney==0.8.0
+      - jieba==0.42.1
+      - jmespath==1.0.1
+      - jupyter-client==7.4.9
+      - jupyter-console==6.6.3
+      - jupyter-events==0.9.0
+      - jupyter-http-over-ws==0.0.8
+      - jupyter-lsp==1.5.1
+      - jupyter-server==2.12.1
+      - jupyter-server-mathjax==0.2.6
+      - jupyter-server-proxy==4.0.0
+      - jupyterlab==4.0.9
+      - jupyterlab-git==0.42.0
+      - jupyterlab-lsp==5.0.1
+      - jupyterlab-widgets==3.0.8
+      - jupytext==1.15.0
+      - kaggle==1.5.16
+      - kaggle-environments==1.14.3
+      - kagglehub==0.1.4
+      - keras==2.13.1
+      - keras-core==0.1.7
+      - keras-cv==0.8.0.dev0
+      - keras-nlp==0.7.0.dev3
+      - keras-tuner==1.3.5
+      - keyring==24.2.0
+      - keyrings-google-artifactregistry-auth==1.1.2
+      - kfp==2.0.1
+      - kfp-pipeline-spec==0.2.2
+      - kfp-server-api==2.0.1
+      - kiwisolver==1.4.4
+      - kmapper==2.0.1
+      - kmodes==0.12.2
+      - korean-lunar-calendar==0.3.1
+      - kornia==0.7.0
+      - kt-legacy==1.0.5
+      - kubernetes==26.1.0
+      - langid==1.1.6
+      - lazy-loader==0.3
+      - learntools==0.3.4
+      - leven==1.0.4
+      - levenshtein==0.23.0
+      - libclang==16.0.6
+      - libpysal==4.9.2
+      - librosa==0.10.1
+      - lightgbm==3.3.2
+      - lightning-utilities==0.10.0
+      - lime==0.2.0.1
+      - line-profiler==4.1.2
+      - linkify-it-py==2.0.2
+      - llvmlite==0.40.1
+      - lml==0.1.0
+      - lunarcalendar==0.0.9
+      - lxml==4.9.3
+      - mako==1.3.0
+      - mapclassify==2.6.0
+      - marisa-trie==1.1.0
+      - markdown==3.4.4
+      - markovify==0.9.4
+      - marshmallow==3.20.1
+      - matplotlib==3.7.4
+      - matplotlib-venn==0.11.9
+      - mccabe==0.7.0
+      - mdit-py-plugins==0.4.0
+      - mdurl==0.1.2
+      - memory-profiler==0.61.0
+      - mercantile==1.2.1
+      - mgwr==2.2.0
+      - missingno==0.5.2
+      - mistune==0.8.4
+      - mizani==0.10.0
+      - ml-dtypes==0.3.1
+      - mlcrate==0.2.0
+      - mlens==0.2.3
+      - mlxtend==0.23.0
+      - mmh3==4.0.1
+      - mne==1.6.0
+      - mnist==0.2.2
+      - mock==5.1.0
+      - momepy==0.7.0
+      - more-itertools==10.1.0
+      - mpld3==0.5.9
+      - mpmath==1.3.0
+      - msgpack==1.0.5
+      - msgpack-numpy==0.4.8
+      - multimethod==1.9.1
+      - multipledispatch==1.0.0
+      - multiprocess==0.70.15
+      - mypy-extensions==1.0.0
+      - namex==0.0.7
+      - nbclassic==1.0.0
+      - nbclient==0.5.13
+      - nbconvert==6.4.5
+      - nbdime==3.2.0
+      - ndindex==1.7
+      - nest-asyncio==1.5.7
+      - netcdf4==1.6.5
+      - networkx==3.1
+      - nibabel==5.2.0
+      - nilearn==0.10.2
+      - ninja==1.11.1.1
+      - nltk==3.2.4
+      - nose==1.3.7
+      - notebook==6.5.5
+      - notebook-executor==0.2
+      - numba==0.57.1
+      - numexpr==2.8.8
+      - numpy==1.23.5
+      - nvidia-ml-py==11.495.46
+      - oauth2client==4.1.3
+      - oauthlib==3.2.2
+      - objsize==0.6.1
+      - odfpy==1.4.1
+      - olefile==0.47
+      - onnx==1.15.0
+      - opencensus==0.11.2
+      - opencensus-context==0.1.3
+      - opencv-contrib-python==4.8.1.78
+      - opencv-python==4.8.1.78
+      - opencv-python-headless==4.8.1.78
+      - openpyxl==3.1.2
+      - openslide-python==1.3.1
+      - opentelemetry-api==1.19.0
+      - opentelemetry-exporter-otlp==1.19.0
+      - opentelemetry-exporter-otlp-proto-common==1.19.0
+      - opentelemetry-exporter-otlp-proto-grpc==1.19.0
+      - opentelemetry-exporter-otlp-proto-http==1.19.0
+      - opentelemetry-proto==1.19.0
+      - opentelemetry-sdk==1.19.0
+      - opentelemetry-semantic-conventions==0.40b0
+      - opt-einsum==3.3.0
+      - optax==0.1.7
+      - optuna==3.5.0
+      - orbax-checkpoint==0.4.7
+      - orderedmultidict==1.0.1
+      - orjson==3.9.5
+      - ortools==9.4.1874
+      - osmnx==1.1.1
+      - overrides==6.5.0
+      - packaging==21.3
+      - pandas==2.1.4
+      - pandas-datareader==0.10.0
+      - pandas-profiling==3.6.6
+      - pandas-summary==0.2.0
+      - pandasql==0.7.3
+      - panel==1.3.4
+      - papermill==2.4.0
+      - param==2.0.1
+      - path==16.9.0
+      - path-py==12.5.0
+      - pathos==0.3.1
+      - patsy==0.5.3
+      - pdf2image==1.16.3
+      - pettingzoo==1.24.0
+      - phik==0.12.3
+      - pillow==9.5.0
+      - platformdirs==4.1.0
+      - plotly==5.16.1
+      - plotly-express==0.4.1
+      - plotnine==0.10.1
+      - pointpats==2.4.0
+      - polars==0.19.19
+      - polyglot==16.7.4
+      - pooch==1.8.0
+      - pox==0.3.3
+      - ppca==0.0.4
+      - ppft==1.7.6.7
+      - preprocessing==0.1.13
+      - prettytable==3.8.0
+      - progressbar2==4.2.0
+      - promise==2.3
+      - pronouncing==0.2.0
+      - prophet==1.1.1
+      - proto-plus==1.22.3
+      - protobuf==3.20.3
+      - psutil==5.9.3
+      - ptxcompiler-cu11==0.7.0.post1
+      - pudb==2023.1
+      - pulp==2.7.0
+      - py-cpuinfo==9.0.0
+      - py-spy==0.3.14
+      - py4j==0.10.9.7
+      - pyaml==23.9.7
+      - pyarabic==0.6.15
+      - pyasn1==0.5.0
+      - pyasn1-modules==0.3.0
+      - pyastronomy==0.20.0
+      - pybind11==2.11.1
+      - pyclipper==1.3.0.post5
+      - pycodestyle==2.11.1
+      - pycparser==2.21
+      - pycryptodome==3.19.0
+      - pyct==0.5.0
+      - pycuda==2023.1
+      - pydantic==1.10.12
+      - pydegensac==0.1.2
+      - pydicom==2.4.3
+      - pydocstyle==6.3.0
+      - pydot==1.4.2
+      - pydub==0.25.1
+      - pyemd==1.0.0
+      - pyerfa==2.0.1.1
+      - pyexcel-io==0.6.6
+      - pyexcel-ods==0.6.0
+      - pyfasttext==0.4.6
+      - pyflakes==3.1.0
+      - pygltflib==1.16.1
+      - pyjwt==2.8.0
+      - pykalman==0.9.5
+      - pyldavis==3.2.2
+      - pylint==3.0.3
+      - pymc3==3.11.5
+      - pymeeus==0.5.12
+      - pymongo==3.13.0
+      - pympler==1.0.1
+      - pynndescent==0.5.11
+      - pynvrtc==9.2
+      - pyocr==0.8.5
+      - pyparsing==3.0.9
+      - pypdf==3.17.2
+      - pysal==23.7
+      - pytesseract==0.3.10
+      - pytest==7.4.3
+      - python-bidi==0.4.2
+      - python-dotenv==1.0.0
+      - python-graphviz==0.20.1
+      - python-levenshtein==0.23.0
+      - python-louvain==0.16
+      - python-lsp-jsonrpc==1.1.2
+      - python-lsp-server==1.9.0
+      - python-slugify==8.0.1
+      - python-utils==3.8.1
+      - pythreejs==2.4.2
+      - pytoolconfig==1.2.6
+      - pytools==2023.1.1
+      - pytorch-ignite==0.4.13
+      - pytorch-lightning==2.1.2
+      - pyupset==0.1.1.post7
+      - pyviz-comms==3.0.0
+      - pywavelets==1.4.1
+      - pyzmq==24.0.1
+      - qgrid==1.3.1
+      - qtconsole==5.5.1
+      - qtpy==2.4.1
+      - quantecon==0.7.1
+      - quantities==0.15.0
+      - qudida==0.0.4
+      - rapidfuzz==3.5.2
+      - rasterio==1.3.9
+      - rasterstats==0.19.0
+      - ray==2.6.3
+      - ray-cpp==2.6.3
+      - regex==2023.8.8
+      - requests-oauthlib==1.3.1
+      - requests-toolbelt==0.10.1
+      - responses==0.18.0
+      - retrying==1.3.4
+      - rgf-python==3.12.0
+      - rich==13.5.2
+      - rope==1.11.0
+      - rouge-score==0.1.2
+      - rtree==1.1.0
+      - s2sphere==0.2.5
+      - s3fs==2023.12.2
+      - s3transfer==0.6.2
+      - safetensors==0.4.1
+      - scattertext==0.1.19
+      - scikit-image==0.21.0
+      - scikit-learn==1.2.2
+      - scikit-learn-intelex==2024.0.1
+      - scikit-multilearn==0.2.0
+      - scikit-optimize==0.9.0
+      - scikit-plot==0.3.7
+      - scikit-surprise==1.1.3
+      - scipy==1.7.3
+      - seaborn==0.12.2
+      - secretstorage==3.3.3
+      - segment-anything==1.0
+      - segregation==2.5
+      - semver==3.0.2
+      - sentencepiece==0.1.99
+      - sentry-sdk==1.39.0
+      - setproctitle==1.3.3
+      - setuptools-git==1.2
+      - setuptools-scm==8.0.4
+      - shap==0.44.0
+      - shimmy==1.3.0
+      - simpervisor==1.0.0
+      - simpleitk==2.3.1
+      - simplejson==3.19.2
+      - six==1.16.0
+      - sklearn-pandas==2.2.0
+      - slicer==0.0.7
+      - smart-open==6.3.0
+      - smhasher==0.150.1
+      - smmap==5.0.0
+      - snowballstemmer==2.2.0
+      - snuggs==1.4.7
+      - soundfile==0.12.1
+      - soupsieve==2.4.1
+      - soxr==0.3.7
+      - spaghetti==1.7.4
+      - spectral==0.23.1
+      - spglm==1.1.0
+      - sphinx-rtd-theme==0.2.4
+      - spint==1.0.7
+      - splot==1.1.5.post1
+      - spopt==0.6.0
+      - spreg==1.4.2
+      - spvcm==0.3.0
+      - sqlalchemy==2.0.20
+      - sqlparse==0.4.4
+      - squarify==0.4.3
+      - stable-baselines3==2.1.0
+      - stanio==0.3.0
+      - starlette==0.27.0
+      - statsmodels==0.14.0
+      - stemming==1.0.1
+      - stop-words==2018.7.23
+      - stopit==1.1.2
+      - stumpy==1.12.0
+      - sympy==1.12
+      - tables==3.9.2
+      - tabulate==0.9.0
+      - tangled-up-in-unicode==0.2.0
+      - tbb==2021.11.0
+      - tenacity==8.2.3
+      - tensorboard==2.13.0
+      - tensorboard-data-server==0.7.1
+      - tensorboard-plugin-profile==2.13.1
+      - tensorboardx==2.6.2.2
+      - tensorflow==2.13.0
+      - tensorflow-addons==0.23.0
+      - tensorflow-cloud==0.1.16
+      - tensorflow-datasets==4.9.2
+      - tensorflow-decision-forests==1.5.0
+      - tensorflow-estimator==2.13.0
+      - tensorflow-hub==0.14.0
+      - tensorflow-io==0.34.0
+      - tensorflow-io-gcs-filesystem==0.34.0
+      - tensorflow-metadata==0.14.0
+      - tensorflow-probability==0.21.0
+      - tensorflow-serving-api==2.13.0
+      - tensorflow-text==2.13.0
+      - tensorflow-transform==0.14.0
+      - tensorflowjs==4.14.0
+      - tensorpack==0.11
+      - tensorstore==0.1.51
+      - termcolor==2.3.0
+      - testpath==0.6.0
+      - text-unidecode==1.3
+      - textblob==0.17.1
+      - texttable==1.7.0
+      - textwrap3==0.9.2
+      - theano==1.0.5
+      - theano-pymc==1.1.2
+      - threadpoolctl==3.2.0
+      - tifffile==2023.8.12
+      - timm==0.9.12
+      - tobler==0.11.2
+      - tokenizers==0.15.0
+      - toml==0.10.2
+      - tomlkit==0.12.3
+      - torch==2.0.0
+      - torchaudio==2.0.1
+      - torchdata==0.7.1
+      - torchinfo==1.8.0
+      - torchmetrics==1.2.1
+      - torchtext==0.15.1
+      - torchvision==0.15.1
+      - tpot==0.12.1
+      - traceml==1.0.8
+      - traittypes==0.2.1
+      - transformers==4.36.0
+      - treelite-runtime==3.2.0
+      - trueskill==0.4.5
+      - tsfresh==0.20.1
+      - typeguard==2.13.3
+      - typing-extensions==4.5.0
+      - typing-inspect==0.9.0
+      - tzdata==2023.3
+      - tzlocal==5.2
+      - uc-micro-py==1.0.2
+      - ujson==5.9.0
+      - umap-learn==0.5.5
+      - unidecode==1.3.7
+      - update-checker==0.18.0
+      - uritemplate==3.0.1
+      - urllib3==1.26.16
+      - urwid==2.3.4
+      - urwid-readline==0.13
+      - uvicorn==0.23.2
+      - uvloop==0.19.0
+      - vaex==4.17.0
+      - vaex-astro==0.9.3
+      - vaex-core==4.17.1
+      - vaex-hdf5==0.14.1
+      - vaex-jupyter==0.8.2
+      - vaex-ml==0.18.3
+      - vaex-server==0.9.0
+      - vaex-viz==0.5.4
+      - vec-noise==1.1.4
+      - vecstack==0.4.0
+      - virtualenv==20.21.0
+      - visions==0.7.5
+      - vowpalwabbit==9.9.0
+      - vtk==9.3.0
+      - wand==0.6.13
+      - wandb==0.16.1
+      - watchfiles==0.21.0
+      - wavio==0.0.8
+      - webencodings==0.5.1
+      - websockets==12.0
+      - werkzeug==3.0.1
+      - wfdb==4.1.2
+      - whatthepatch==1.0.5
+      - widgetsnbextension==3.6.6
+      - witwidget==1.8.1
+      - woodwork==0.27.0
+      - wordcloud==1.9.2
+      - wordsegment==1.3.1
+      - wrapt==1.15.0
+      - wurlitzer==3.0.3
+      - xarray==2023.12.0
+      - xarray-einstats==0.6.0
+      - xgboost==2.0.2
+      - xvfbwrapper==0.2.9
+      - xxhash==3.4.1
+      - yapf==0.40.2
+      - ydata-profiling==4.5.1
+      - yellowbrick==1.5
+prefix: /opt/conda

wandb/run-20240103_105541-kk0m5fl8/files/config.yaml

@@ -0,0 +1,737 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.12
+    cli_version: 0.16.1
+    framework: huggingface
+    huggingface_version: 4.36.0
+    is_jupyter_run: true
+    is_kaggle_kernel: true
+    start_time: 1704279341.501455
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 105
+      2:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 105
+      3:
+      - 7
+      - 23
+      4: 3.10.12
+      5: 0.16.1
+      6: 4.36.0
+      8:
+      - 1
+      - 2
+      - 5
+      9:
+        1: transformers_trainer
+      13: linux-x86_64
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/rouge2_precision
+      5: 1
+      6:
+      - 1
+    - 1: eval/rouge2_recall
+      5: 1
+      6:
+      - 1
+    - 1: eval/rouge2_fmeasure
+      5: 1
+      6:
+      - 1
+    - 1: eval/runtime
+      5: 1
+      6:
+      - 1
+    - 1: eval/samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: eval/steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_runtime
+      5: 1
+      6:
+      - 1
+    - 1: train/train_samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/total_flos
+      5: 1
+      6:
+      - 1
+    - 1: train/train_loss
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 50265
+max_encoder_position_embeddings:
+  desc: null
+  value: 16384
+max_decoder_position_embeddings:
+  desc: null
+  value: 1024
+d_model:
+  desc: null
+  value: 768
+encoder_ffn_dim:
+  desc: null
+  value: 3072
+encoder_layers:
+  desc: null
+  value: 6
+encoder_attention_heads:
+  desc: null
+  value: 12
+decoder_ffn_dim:
+  desc: null
+  value: 3072
+decoder_layers:
+  desc: null
+  value: 6
+decoder_attention_heads:
+  desc: null
+  value: 12
+dropout:
+  desc: null
+  value: 0.1
+attention_dropout:
+  desc: null
+  value: 0.0
+activation_dropout:
+  desc: null
+  value: 0.0
+activation_function:
+  desc: null
+  value: gelu
+init_std:
+  desc: null
+  value: 0.02
+encoder_layerdrop:
+  desc: null
+  value: 0.0
+decoder_layerdrop:
+  desc: null
+  value: 0.0
+classifier_dropout:
+  desc: null
+  value: 0.0
+use_cache:
+  desc: null
+  value: false
+num_hidden_layers:
+  desc: null
+  value: 6
+attention_window:
+  desc: null
+  value:
+  - 1024
+  - 1024
+  - 1024
+  - 1024
+  - 1024
+  - 1024
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: null
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: true
+is_encoder_decoder:
+  desc: null
+  value: true
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 512
+min_length:
+  desc: null
+  value: 100
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: true
+num_beams:
+  desc: null
+  value: 2
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 2.0
+no_repeat_ngram_size:
+  desc: null
+  value: 3
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value: null
+architectures:
+  desc: null
+  value:
+  - LEDForConditionalGeneration
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+    '2': LABEL_2
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+    LABEL_2: 2
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 0
+pad_token_id:
+  desc: null
+  value: 1
+eos_token_id:
+  desc: null
+  value: 2
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: 2
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: allenai/led-base-16384
+transformers_version:
+  desc: null
+  value: 4.36.0
+classif_dropout:
+  desc: null
+  value: 0.0
+model_type:
+  desc: null
+  value: led
+output_dir:
+  desc: null
+  value: ./
+overwrite_output_dir:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: false
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+evaluation_strategy:
+  desc: null
+  value: steps
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 2
+per_device_eval_batch_size:
+  desc: null
+  value: 2
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 4
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 5.0e-05
+weight_decay:
+  desc: null
+  value: 0.0
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 1.0
+num_train_epochs:
+  desc: null
+  value: 1
+max_steps:
+  desc: null
+  value: -1
+lr_scheduler_type:
+  desc: null
+  value: linear
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 0
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/Jan03_11-05-09_416a3b7a3d3d
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 5
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 10
+save_total_limit:
+  desc: null
+  value: 2
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+save_only_model:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_cpu:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: null
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: false
+fp16:
+  desc: null
+  value: true
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: auto
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: null
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: null
+tpu_num_cores:
+  desc: null
+  value: null
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: []
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: 10
+dataloader_num_workers:
+  desc: null
+  value: 0
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: ./
+disable_tqdm:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+label_names:
+  desc: null
+  value: null
+load_best_model_at_end:
+  desc: null
+  value: false
+metric_for_best_model:
+  desc: null
+  value: null
+greater_is_better:
+  desc: null
+  value: null
+ignore_data_skip:
+  desc: null
+  value: false
+fsdp:
+  desc: null
+  value: []
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value:
+    min_num_params: 0
+    xla: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+deepspeed:
+  desc: null
+  value: null
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: adamw_torch
+optim_args:
+  desc: null
+  value: null
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: false
+length_column_name:
+  desc: null
+  value: length
+report_to:
+  desc: null
+  value:
+  - tensorboard
+  - wandb
+ddp_find_unused_parameters:
+  desc: null
+  value: null
+ddp_bucket_cap_mb:
+  desc: null
+  value: null
+ddp_broadcast_buffers:
+  desc: null
+  value: null
+dataloader_pin_memory:
+  desc: null
+  value: true
+dataloader_persistent_workers:
+  desc: null
+  value: false
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: false
+resume_from_checkpoint:
+  desc: null
+  value: null
+hub_model_id:
+  desc: null
+  value: null
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+hub_always_push:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: false
+gradient_checkpointing_kwargs:
+  desc: null
+  value: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+fp16_backend:
+  desc: null
+  value: auto
+push_to_hub_model_id:
+  desc: null
+  value: null
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: null
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: null
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: false
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null
+sortish_sampler:
+  desc: null
+  value: false
+predict_with_generate:
+  desc: null
+  value: true
+generation_max_length:
+  desc: null
+  value: null
+generation_num_beams:
+  desc: null
+  value: null
+generation_config:
+  desc: null
+  value: null

wandb/run-20240103_105541-kk0m5fl8/files/output.log

@@ -0,0 +1,3 @@
+
+You're using a LEDTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+/opt/conda/lib/python3.10/site-packages/transformers/generation/utils.py:1518: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration )

wandb/run-20240103_105541-kk0m5fl8/files/requirements.txt

@@ -0,0 +1,845 @@
+absl-py==1.4.0
+accelerate==0.25.0
+access==1.1.9
+affine==2.4.0
+aiobotocore==2.8.0
+aiohttp-cors==0.7.0
+aiohttp==3.8.5
+aioitertools==0.11.0
+aiorwlock==1.3.0
+aiosignal==1.3.1
+albumentations==1.3.1
+alembic==1.13.0
+altair==5.2.0
+annotated-types==0.6.0
+annoy==1.17.3
+ansiwrap==0.8.4
+anyio==3.7.1
+apache-beam==2.46.0
+aplus==0.11.0
+appdirs==1.4.4
+archspec==0.2.2
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+array-record==0.4.1
+arrow==1.2.3
+arviz==0.12.1
+astroid==3.0.2
+astropy-iers-data==0.2023.12.11.0.31.11
+astropy==6.0.0
+asttokens==2.2.1
+astunparse==1.6.3
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==23.1.0
+audioread==3.0.1
+autopep8==2.0.4
+babel==2.12.1
+backcall==0.2.0
+backoff==2.2.1
+backports.functools-lru-cache==1.6.5
+bayesian-optimization==1.4.3
+bayespy==0.5.26
+beatrix-jupyterlab==2023.814.150030
+beautifulsoup4==4.12.2
+bidict==0.22.1
+biopython==1.81
+blake3==0.2.1
+bleach==6.0.0
+blessed==1.20.0
+blinker==1.7.0
+blis==0.7.10
+blosc2==2.3.2
+bokeh==3.3.2
+boltons==23.0.0
+boruta==0.3
+boto3==1.26.100
+botocore==1.33.1
+bq-helper==0.4.1
+bqplot==0.12.42
+branca==0.7.0
+brewer2mpl==1.4.1
+brotlipy==0.7.0
+cached-property==1.5.2
+cachetools==4.2.4
+cartopy==0.22.0
+catalogue==2.0.10
+catalyst==22.4
+catboost==1.2.2
+category-encoders==2.6.3
+certifi==2023.11.17
+cesium==0.12.1
+cffi==1.15.1
+cftime==1.6.3
+charset-normalizer==3.2.0
+chex==0.1.85
+cleverhans==4.0.0
+click-plugins==1.1.1
+click==8.1.7
+cligj==0.7.2
+cloud-tpu-client==0.10
+cloud-tpu-profiler==2.4.0
+cloudpathlib==0.16.0
+cloudpickle==2.2.1
+cmdstanpy==1.2.0
+cmudict==1.0.15
+colorama==0.4.6
+colorcet==3.0.1
+colorful==0.5.5
+colorlog==6.8.0
+colorlover==0.3.0
+comm==0.1.4
+conda-libmamba-solver==23.7.0
+conda-package-handling==2.2.0
+conda-package-streaming==0.9.0
+conda==23.7.4
+confection==0.1.4
+contextily==1.4.0
+contourpy==1.1.0
+convertdate==2.4.0
+crcmod==1.7
+cryptography==41.0.3
+cubinlinker-cu11==0.3.0.post1
+cubinlinker==0.3.0
+cuda-python==11.8.3
+cudf==23.8.0
+cufflinks==0.17.3
+cuml==23.8.0
+cupy==12.3.0
+cvxcanon==0.1.2
+cycler==0.11.0
+cymem==2.0.8
+cysignals==1.11.4
+cython==3.0.0
+cytoolz==0.12.2
+daal4py==2024.0.1
+daal==2024.0.1
+dacite==1.8.1
+dask-cuda==23.8.0
+dask-cudf==23.8.0
+dask==2023.12.0
+dataclasses-json==0.6.3
+datasets==2.1.0
+datashader==0.16.0
+datatile==1.0.3
+db-dtypes==1.1.1
+deap==1.4.1
+debugpy==1.6.7.post1
+decorator==5.1.1
+defusedxml==0.7.1
+delorean==1.0.0
+deprecat==2.1.1
+deprecated==1.2.14
+deprecation==2.1.0
+descartes==1.1.0
+dill==0.3.7
+dipy==1.7.0
+distlib==0.3.7
+distributed==2023.12.0
+distro==1.8.0
+dm-tree==0.1.8
+docker-pycreds==0.4.0
+docker==6.1.3
+docopt==0.6.2
+docstring-parser==0.15
+docstring-to-markdown==0.13
+docutils==0.20.1
+earthengine-api==0.1.383
+easydict==1.11
+easyocr==1.7.1
+ecos==2.0.12
+eli5==0.13.0
+emoji==2.9.0
+en-core-web-lg==3.7.1
+en-core-web-sm==3.7.1
+entrypoints==0.4
+ephem==4.1.5
+esda==2.5.1
+essentia==2.1b6.dev1110
+et-xmlfile==1.1.0
+etils==1.4.1
+exceptiongroup==1.1.3
+executing==1.2.0
+explainable-ai-sdk==1.3.3
+farama-notifications==0.0.4
+fastai==2.7.13
+fastapi==0.101.1
+fastavro==1.8.2
+fastcore==1.5.29
+fastdownload==0.0.7
+fasteners==0.18
+fastjsonschema==2.18.0
+fastprogress==1.0.3
+fastrlock==0.8.2
+fasttext==0.9.2
+fbpca==1.0
+feather-format==0.4.1
+featuretools==1.28.0
+filelock==3.12.2
+fiona==1.9.5
+fitter==1.6.0
+flake8==6.1.0
+flashtext==2.7
+flask==3.0.0
+flatbuffers==23.5.26
+flax==0.7.5
+flit-core==3.9.0
+folium==0.15.1
+fonttools==4.42.1
+fqdn==1.5.1
+frozendict==2.3.10
+frozenlist==1.4.0
+fsspec==2023.12.2
+funcy==2.0
+fury==0.9.0
+future==0.18.3
+fuzzywuzzy==0.18.0
+gast==0.4.0
+gatspy==0.3
+gcsfs==2023.6.0
+gensim==4.3.2
+geographiclib==2.0
+geohash==1.0
+geojson==3.1.0
+geopandas==0.14.1
+geoplot==0.5.1
+geopy==2.4.1
+geoviews==1.11.0
+ggplot==0.11.5
+giddy==2.3.4
+gitdb==4.0.10
+gitpython==3.1.32
+google-ai-generativelanguage==0.4.0
+google-api-core==2.11.1
+google-api-python-client==2.111.0
+google-apitools==0.5.31
+google-auth-httplib2==0.1.0
+google-auth-oauthlib==1.0.0
+google-auth==2.22.0
+google-cloud-aiplatform==0.6.0a1
+google-cloud-artifact-registry==1.8.3
+google-cloud-automl==1.0.1
+google-cloud-bigquery==2.34.4
+google-cloud-bigtable==1.7.3
+google-cloud-core==2.3.3
+google-cloud-datastore==2.18.0
+google-cloud-dlp==3.12.2
+google-cloud-language==2.12.0
+google-cloud-monitoring==2.15.1
+google-cloud-pubsub==2.18.3
+google-cloud-pubsublite==1.8.3
+google-cloud-recommendations-ai==0.7.1
+google-cloud-resource-manager==1.10.3
+google-cloud-spanner==3.40.1
+google-cloud-storage==1.44.0
+google-cloud-translate==3.12.1
+google-cloud-videointelligence==2.12.0
+google-cloud-vision==2.8.0
+google-crc32c==1.5.0
+google-generativeai==0.3.0
+google-pasta==0.2.0
+google-resumable-media==2.5.0
+googleapis-common-protos==1.60.0
+gplearn==0.4.2
+gpustat==1.0.0
+gpxpy==1.6.2
+graphviz==0.20.1
+greenlet==2.0.2
+grpc-google-iam-v1==0.12.6
+grpcio-status==1.48.1
+grpcio==1.51.1
+gviz-api==1.10.0
+gym-notices==0.0.8
+gym==0.26.2
+gymnasium-notices==0.0.1
+gymnasium==0.29.0
+h11==0.14.0
+h2o==3.44.0.2
+h5py==3.9.0
+haversine==2.8.0
+hdfs==2.7.2
+hep-ml==0.7.2
+hijri-converter==2.3.1
+hmmlearn==0.3.0
+holidays==0.24
+holoviews==1.18.1
+hpsklearn==0.1.0
+html5lib==1.1
+htmlmin==0.1.12
+httplib2==0.21.0
+httptools==0.6.1
+huggingface-hub==0.19.4
+humanize==4.9.0
+hunspell==0.5.5
+husl==4.0.3
+hydra-slayer==0.4.1
+hyperopt==0.2.7
+hypertools==0.8.0
+idna==3.4
+igraph==0.11.3
+imagecodecs==2023.9.18
+imagehash==4.3.1
+imageio==2.31.1
+imbalanced-learn==0.11.0
+imgaug==0.4.0
+importlib-metadata==6.8.0
+importlib-resources==5.13.0
+inequality==1.0.1
+iniconfig==2.0.0
+ipydatawidgets==4.3.5
+ipykernel==6.25.1
+ipyleaflet==0.18.0
+ipympl==0.7.0
+ipython-genutils==0.2.0
+ipython-sql==0.5.0
+ipython==8.14.0
+ipyvolume==0.6.3
+ipyvue==1.10.1
+ipyvuetify==1.8.10
+ipywebrtc==0.6.0
+ipywidgets==7.7.1
+isoduration==20.11.0
+isort==5.13.1
+isoweek==1.3.3
+itsdangerous==2.1.2
+janome==0.5.0
+jaraco.classes==3.3.0
+jax==0.4.21
+jaxlib==0.4.21+cuda11.cudnn86
+jedi==0.19.0
+jeepney==0.8.0
+jieba==0.42.1
+jinja2==3.1.2
+jmespath==1.0.1
+joblib==1.3.2
+json5==0.9.14
+jsonpatch==1.32
+jsonpointer==2.0
+jsonschema-specifications==2023.7.1
+jsonschema==4.19.0
+jupyter-client==7.4.9
+jupyter-console==6.6.3
+jupyter-core==5.3.1
+jupyter-events==0.9.0
+jupyter-http-over-ws==0.0.8
+jupyter-lsp==1.5.1
+jupyter-server-mathjax==0.2.6
+jupyter-server-proxy==4.0.0
+jupyter-server-terminals==0.4.4
+jupyter-server==2.12.1
+jupyterlab-git==0.42.0
+jupyterlab-lsp==5.0.1
+jupyterlab-pygments==0.2.2
+jupyterlab-server==2.24.0
+jupyterlab-widgets==3.0.8
+jupyterlab==4.0.5
+jupytext==1.15.0
+kaggle-environments==1.14.3
+kaggle==1.5.16
+kagglehub==0.1.4
+keras-core==0.1.7
+keras-cv==0.8.0.dev0
+keras-nlp==0.7.0.dev3
+keras-tuner==1.3.5
+keras==2.13.1
+keyring==24.2.0
+keyrings.google-artifactregistry-auth==1.1.2
+kfp-pipeline-spec==0.2.2
+kfp-server-api==2.0.1
+kfp==2.0.1
+kiwisolver==1.4.4
+kmapper==2.0.1
+kmodes==0.12.2
+korean-lunar-calendar==0.3.1
+kornia==0.7.0
+kt-legacy==1.0.5
+kubernetes==26.1.0
+langcodes==3.3.0
+langid==1.1.6
+lazy-loader==0.3
+learntools==0.3.4
+leven==1.0.4
+levenshtein==0.23.0
+libclang==16.0.6
+libmambapy==1.5.0
+libpysal==4.9.2
+librosa==0.10.1
+lightgbm==3.3.2
+lightning-utilities==0.10.0
+lime==0.2.0.1
+line-profiler==4.1.2
+linkify-it-py==2.0.2
+llvmlite==0.40.1
+lml==0.1.0
+locket==1.0.0
+lunarcalendar==0.0.9
+lxml==4.9.3
+lz4==4.3.2
+mako==1.3.0
+mamba==1.5.0
+mapclassify==2.6.0
+marisa-trie==1.1.0
+markdown-it-py==3.0.0
+markdown==3.4.4
+markovify==0.9.4
+markupsafe==2.1.3
+marshmallow==3.20.1
+matplotlib-inline==0.1.6
+matplotlib-venn==0.11.9
+matplotlib==3.7.4
+mccabe==0.7.0
+mdit-py-plugins==0.4.0
+mdurl==0.1.0
+memory-profiler==0.61.0
+menuinst==2.0.1
+mercantile==1.2.1
+mgwr==2.2.0
+missingno==0.5.2
+mistune==0.8.4
+mizani==0.10.0
+ml-dtypes==0.3.1
+mlcrate==0.2.0
+mlens==0.2.3
+mlxtend==0.23.0
+mmh3==4.0.1
+mne==1.6.0
+mnist==0.2.2
+mock==5.1.0
+momepy==0.7.0
+more-itertools==10.1.0
+mpld3==0.5.9
+mpmath==1.3.0
+msgpack-numpy==0.4.8
+msgpack==1.0.5
+multidict==6.0.4
+multimethod==1.9.1
+multipledispatch==1.0.0
+multiprocess==0.70.15
+munkres==1.1.4
+murmurhash==1.0.10
+mypy-extensions==1.0.0
+namex==0.0.7
+nb-conda-kernels==2.3.1
+nb-conda==2.2.1
+nbclassic==1.0.0
+nbclient==0.5.13
+nbconvert==6.4.5
+nbdime==3.2.0
+nbformat==5.9.2
+ndindex==1.7
+nest-asyncio==1.5.6
+netcdf4==1.6.5
+networkx==3.1
+nibabel==5.2.0
+nilearn==0.10.2
+ninja==1.11.1.1
+nltk==3.2.4
+nose==1.3.7
+notebook-executor==0.2
+notebook-shim==0.2.3
+notebook==6.5.5
+numba==0.57.1
+numexpr==2.8.8
+numpy==1.23.5
+nvidia-ml-py==11.495.46
+nvtx==0.2.8
+oauth2client==4.1.3
+oauthlib==3.2.2
+objsize==0.6.1
+odfpy==1.4.1
+olefile==0.47
+onnx==1.15.0
+opencensus-context==0.1.3
+opencensus==0.11.2
+opencv-contrib-python==4.8.1.78
+opencv-python-headless==4.8.1.78
+opencv-python==4.8.1.78
+openpyxl==3.1.2
+openslide-python==1.3.1
+opentelemetry-api==1.19.0
+opentelemetry-exporter-otlp-proto-common==1.19.0
+opentelemetry-exporter-otlp-proto-grpc==1.19.0
+opentelemetry-exporter-otlp-proto-http==1.19.0
+opentelemetry-exporter-otlp==1.19.0
+opentelemetry-proto==1.19.0
+opentelemetry-sdk==1.19.0
+opentelemetry-semantic-conventions==0.40b0
+opt-einsum==3.3.0
+optax==0.1.7
+optuna==3.5.0
+orbax-checkpoint==0.4.7
+orderedmultidict==1.0.1
+orjson==3.9.5
+ortools==9.4.1874
+osmnx==1.1.1
+overrides==6.5.0
+packaging==21.3
+pandas-datareader==0.10.0
+pandas-profiling==3.6.6
+pandas-summary==0.2.0
+pandas==2.0.3
+pandasql==0.7.3
+pandocfilters==1.5.0
+panel==1.3.4
+papermill==2.4.0
+param==2.0.1
+parso==0.8.3
+partd==1.4.1
+path.py==12.5.0
+path==16.9.0
+pathos==0.3.1
+pathy==0.10.1
+patsy==0.5.3
+pdf2image==1.16.3
+pettingzoo==1.24.0
+pexpect==4.8.0
+phik==0.12.3
+pickleshare==0.7.5
+pillow==10.1.0
+pip==23.2.1
+pkgutil-resolve-name==1.3.10
+platformdirs==4.1.0
+plotly-express==0.4.1
+plotly==5.16.1
+plotnine==0.10.1
+pluggy==1.2.0
+pointpats==2.4.0
+polars==0.19.19
+polyglot==16.7.4
+pooch==1.8.0
+pox==0.3.3
+ppca==0.0.4
+ppft==1.7.6.7
+preprocessing==0.1.13
+preshed==3.0.9
+prettytable==3.8.0
+progressbar2==4.2.0
+prometheus-client==0.17.1
+promise==2.3
+prompt-toolkit==3.0.39
+pronouncing==0.2.0
+prophet==1.1.1
+proto-plus==1.22.3
+protobuf==3.20.3
+psutil==5.9.3
+ptxcompiler-cu11==0.7.0.post1
+ptxcompiler==0.8.1
+ptyprocess==0.7.0
+pudb==2023.1
+pulp==2.7.0
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+py-spy==0.3.14
+py4j==0.10.9.7
+pyaml==23.9.7
+pyarabic==0.6.15
+pyarrow==11.0.0
+pyasn1-modules==0.2.7
+pyasn1==0.4.8
+pyastronomy==0.20.0
+pybind11==2.11.1
+pyclipper==1.3.0.post5
+pycodestyle==2.11.1
+pycosat==0.6.4
+pycparser==2.21
+pycryptodome==3.19.0
+pyct==0.5.0
+pycuda==2023.1
+pydantic-core==2.14.5
+pydantic==1.10.12
+pydegensac==0.1.2
+pydicom==2.4.3
+pydocstyle==6.3.0
+pydot==1.4.2
+pydub==0.25.1
+pyemd==1.0.0
+pyerfa==2.0.1.1
+pyexcel-io==0.6.6
+pyexcel-ods==0.6.0
+pyfasttext==0.4.6
+pyflakes==3.1.0
+pygltflib==1.16.1
+pygments==2.16.1
+pyjwt==2.8.0
+pykalman==0.9.5
+pyldavis==3.2.2
+pylibraft==23.8.0
+pylint==3.0.3
+pymc3==3.11.5
+pymeeus==0.5.12
+pymongo==3.13.0
+pympler==1.0.1
+pynndescent==0.5.11
+pynvml==11.4.1
+pynvrtc==9.2
+pyocr==0.8.5
+pyopenssl==23.2.0
+pyparsing==3.0.9
+pypdf==3.17.2
+pyproj==3.6.1
+pysal==23.7
+pyshp==2.3.1
+pysocks==1.7.1
+pytesseract==0.3.10
+pytest==7.4.3
+python-bidi==0.4.2
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-json-logger==2.0.7
+python-levenshtein==0.23.0
+python-louvain==0.16
+python-lsp-jsonrpc==1.1.2
+python-lsp-server==1.9.0
+python-slugify==8.0.1
+python-utils==3.8.1
+pythreejs==2.4.2
+pytoolconfig==1.2.6
+pytools==2023.1.1
+pytorch-ignite==0.4.13
+pytorch-lightning==2.1.2
+pytz==2023.3
+pyu2f==0.1.5
+pyupset==0.1.1.post7
+pyviz-comms==3.0.0
+pywavelets==1.4.1
+pyyaml==6.0.1
+pyzmq==24.0.1
+qgrid==1.3.1
+qtconsole==5.5.1
+qtpy==2.4.1
+quantecon==0.7.1
+quantities==0.15.0
+qudida==0.0.4
+raft-dask==23.8.0
+rapidfuzz==3.5.2
+rasterio==1.3.9
+rasterstats==0.19.0
+ray-cpp==2.6.3
+ray==2.6.3
+referencing==0.30.2
+regex==2023.8.8
+requests-oauthlib==1.3.1
+requests-toolbelt==0.10.1
+requests==2.31.0
+responses==0.18.0
+retrying==1.3.3
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rgf-python==3.12.0
+rich==13.5.2
+rmm==23.8.0
+rope==1.11.0
+rouge-score==0.1.2
+rpds-py==0.9.2
+rsa==4.9
+rtree==1.1.0
+ruamel-yaml-conda==0.15.100
+ruamel.yaml.clib==0.2.7
+ruamel.yaml==0.17.32
+s2sphere==0.2.5
+s3fs==2023.12.2
+s3transfer==0.6.2
+safetensors==0.4.1
+scattertext==0.1.19
+scikit-image==0.21.0
+scikit-learn-intelex==2024.0.1
+scikit-learn==1.2.2
+scikit-multilearn==0.2.0
+scikit-optimize==0.9.0
+scikit-plot==0.3.7
+scikit-surprise==1.1.3
+scipy==1.11.4
+seaborn==0.12.2
+secretstorage==3.3.3
+segment-anything==1.0
+segregation==2.5
+semver==3.0.2
+send2trash==1.8.2
+sentencepiece==0.1.99
+sentry-sdk==1.39.0
+setproctitle==1.3.3
+setuptools-git==1.2
+setuptools-scm==8.0.4
+setuptools==68.1.2
+shap==0.44.0
+shapely==1.8.5.post1
+shellingham==1.5.4
+shimmy==1.3.0
+simpervisor==1.0.0
+simpleitk==2.3.1
+simplejson==3.19.2
+six==1.16.0
+sklearn-pandas==2.2.0
+slicer==0.0.7
+smart-open==6.3.0
+smhasher==0.150.1
+smmap==5.0.0
+sniffio==1.3.0
+snowballstemmer==2.2.0
+snuggs==1.4.7
+sortedcontainers==2.4.0
+soundfile==0.12.1
+soupsieve==2.3.2.post1
+soxr==0.3.7
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spacy==3.7.2
+spaghetti==1.7.4
+spectral==0.23.1
+spglm==1.1.0
+sphinx-rtd-theme==0.2.4
+spint==1.0.7
+splot==1.1.5.post1
+spopt==0.6.0
+spreg==1.4.2
+spvcm==0.3.0
+sqlalchemy==2.0.20
+sqlparse==0.4.4
+squarify==0.4.3
+srsly==2.4.8
+stable-baselines3==2.1.0
+stack-data==0.6.2
+stanio==0.3.0
+starlette==0.27.0
+statsmodels==0.14.0
+stemming==1.0.1
+stop-words==2018.7.23
+stopit==1.1.2
+stumpy==1.12.0
+sympy==1.12
+tables==3.9.2
+tabulate==0.9.0
+tangled-up-in-unicode==0.2.0
+tbb==2021.11.0
+tblib==3.0.0
+tenacity==8.2.3
+tensorboard-data-server==0.7.1
+tensorboard-plugin-profile==2.13.1
+tensorboard==2.13.0
+tensorboardx==2.6.2.2
+tensorflow-addons==0.23.0
+tensorflow-cloud==0.1.16
+tensorflow-datasets==4.9.2
+tensorflow-decision-forests==1.5.0
+tensorflow-estimator==2.13.0
+tensorflow-hub==0.14.0
+tensorflow-io-gcs-filesystem==0.34.0
+tensorflow-io==0.34.0
+tensorflow-metadata==0.14.0
+tensorflow-probability==0.21.0
+tensorflow-serving-api==2.13.0
+tensorflow-text==2.13.0
+tensorflow-transform==0.14.0
+tensorflow==2.13.0
+tensorflowjs==4.14.0
+tensorpack==0.11
+tensorstore==0.1.51
+termcolor==2.3.0
+terminado==0.17.1
+testpath==0.6.0
+text-unidecode==1.3
+textblob==0.17.1
+texttable==1.7.0
+textwrap3==0.9.2
+theano-pymc==1.1.2
+theano==1.0.5
+thinc==8.2.1
+threadpoolctl==3.2.0
+tifffile==2023.8.12
+timm==0.9.12
+tinycss2==1.2.1
+tobler==0.11.2
+tokenizers==0.15.0
+toml==0.10.2
+tomli==2.0.1
+tomlkit==0.12.3
+toolz==0.12.0
+torch==2.0.0
+torchaudio==2.0.1
+torchdata==0.7.1
+torchinfo==1.8.0
+torchmetrics==1.2.1
+torchtext==0.15.1
+torchvision==0.15.1
+tornado==6.3.3
+tpot==0.12.1
+tqdm==4.66.1
+traceml==1.0.8
+traitlets==5.9.0
+traittypes==0.2.1
+transformers==4.36.0
+treelite-runtime==3.2.0
+treelite==3.2.0
+trueskill==0.4.5
+truststore==0.8.0
+tsfresh==0.20.1
+typeguard==2.13.3
+typer==0.9.0
+typing-extensions==4.5.0
+typing-inspect==0.9.0
+typing-utils==0.1.0
+tzdata==2023.3
+tzlocal==5.2
+uc-micro-py==1.0.2
+ucx-py==0.33.0
+ujson==5.9.0
+umap-learn==0.5.5
+unicodedata2==15.1.0
+unidecode==1.3.7
+update-checker==0.18.0
+uri-template==1.3.0
+uritemplate==3.0.1
+urllib3==1.26.15
+urwid-readline==0.13
+urwid==2.3.4
+uvicorn==0.23.2
+uvloop==0.19.0
+vaex-astro==0.9.3
+vaex-core==4.17.1
+vaex-hdf5==0.14.1
+vaex-jupyter==0.8.2
+vaex-ml==0.18.3
+vaex-server==0.9.0
+vaex-viz==0.5.4
+vaex==4.17.0
+vec-noise==1.1.4
+vecstack==0.4.0
+virtualenv==20.21.0
+visions==0.7.5
+vowpalwabbit==9.9.0
+vtk==9.3.0
+wand==0.6.13
+wandb==0.16.1
+wasabi==1.1.2
+watchfiles==0.21.0
+wavio==0.0.8
+wcwidth==0.2.6
+weasel==0.3.4
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.6.2
+websockets==12.0
+werkzeug==3.0.1
+wfdb==4.1.2
+whatthepatch==1.0.5
+wheel==0.41.2
+widgetsnbextension==3.6.6
+witwidget==1.8.1
+woodwork==0.27.0
+wordcloud==1.9.2
+wordsegment==1.3.1
+wrapt==1.15.0
+wurlitzer==3.0.3
+xarray-einstats==0.6.0
+xarray==2023.12.0
+xgboost==2.0.2
+xvfbwrapper==0.2.9
+xxhash==3.4.1
+xyzservices==2023.10.1
+yapf==0.40.2
+yarl==1.9.2
+ydata-profiling==4.5.1
+yellowbrick==1.5
+zict==3.0.0
+zipp==3.16.2
+zstandard==0.22.0

wandb/run-20240103_105541-kk0m5fl8/files/wandb-metadata.json

@@ -0,0 +1,62 @@
+{
+    "os": "Linux-5.15.133+-x86_64-with-glibc2.35",
+    "python": "3.10.12",
+    "heartbeatAt": "2024-01-03T10:55:42.744474",
+    "startedAt": "2024-01-03T10:55:41.493401",
+    "docker": null,
+    "cuda": null,
+    "args": [],
+    "state": "running",
+    "program": "kaggle.ipynb",
+    "codePathLocal": null,
+    "root": "/kaggle/working",
+    "host": "416a3b7a3d3d",
+    "username": "root",
+    "executable": "/opt/conda/bin/python3.10",
+    "cpu_count": 2,
+    "cpu_count_logical": 4,
+    "cpu_freq": {
+        "current": 2000.18,
+        "min": 0.0,
+        "max": 0.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2000.18,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.18,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.18,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.18,
+            "min": 0.0,
+            "max": 0.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 8062.387607574463,
+            "used": 5341.223731994629
+        }
+    },
+    "gpu": "Tesla P100-PCIE-16GB",
+    "gpu_count": 1,
+    "gpu_devices": [
+        {
+            "name": "Tesla P100-PCIE-16GB",
+            "memory_total": 17071734784
+        }
+    ],
+    "memory": {
+        "total": 31.357559204101562
+    }
+}

wandb/run-20240103_105541-kk0m5fl8/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 2.7651, "train/learning_rate": 1.6129032258064516e-06, "train/epoch": 0.99, "train/global_step": 31, "_timestamp": 1704281273.7608829, "_runtime": 1932.2594277858734, "_step": 11, "eval/loss": 2.7667200565338135, "eval/rouge2_precision": 0.15, "eval/rouge2_recall": 0.0913, "eval/rouge2_fmeasure": 0.1075, "eval/runtime": 195.4654, "eval/samples_per_second": 0.128, "eval/steps_per_second": 0.067, "train/train_runtime": 1361.2342, "train/train_samples_per_second": 0.184, "train/train_steps_per_second": 0.023, "train/total_flos": 1339301598068736.0, "train/train_loss": 2.9218551266577935}

wandb/run-20240103_105541-kk0m5fl8/logs/debug.log

@@ -0,0 +1,55 @@
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Configure stats pid to 99
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_init.py:_log_setup():524] Logging user logs to /kaggle/working/wandb/run-20240103_105541-kk0m5fl8/logs/debug.log
+2024-01-03 10:55:41,495 INFO    MainThread:99 [wandb_init.py:_log_setup():525] Logging internal logs to /kaggle/working/wandb/run-20240103_105541-kk0m5fl8/logs/debug-internal.log
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x78c0792cf100>
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():564] calling init triggers
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+config: {}
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():614] starting backend
+2024-01-03 10:55:41,496 INFO    MainThread:99 [wandb_init.py:init():618] setting up manager
+2024-01-03 10:55:41,498 INFO    MainThread:99 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-01-03 10:55:41,501 INFO    MainThread:99 [wandb_init.py:init():624] backend started and connected
+2024-01-03 10:55:41,513 INFO    MainThread:99 [wandb_run.py:_label_probe_notebook():1294] probe notebook
+2024-01-03 10:55:42,150 INFO    MainThread:99 [wandb_init.py:init():716] updated telemetry
+2024-01-03 10:55:42,164 INFO    MainThread:99 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2024-01-03 10:55:42,671 INFO    MainThread:99 [wandb_run.py:_on_init():2254] communicating current version
+2024-01-03 10:55:42,725 INFO    MainThread:99 [wandb_run.py:_on_init():2263] got version response 
+2024-01-03 10:55:42,725 INFO    MainThread:99 [wandb_init.py:init():800] starting run threads in backend
+2024-01-03 10:56:12,751 INFO    MainThread:99 [wandb_run.py:_console_start():2233] atexit reg
+2024-01-03 10:56:12,751 INFO    MainThread:99 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2024-01-03 10:56:12,752 INFO    MainThread:99 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2024-01-03 10:56:12,752 INFO    MainThread:99 [wandb_run.py:_redirect():2178] Redirects installed.
+2024-01-03 10:56:12,753 INFO    MainThread:99 [wandb_init.py:init():841] run started, returning control to user process
+2024-01-03 10:56:12,760 INFO    MainThread:99 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 50265, 'max_encoder_position_embeddings': 16384, 'max_decoder_position_embeddings': 1024, 'd_model': 768, 'encoder_ffn_dim': 3072, 'encoder_layers': 6, 'encoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'decoder_layers': 6, 'decoder_attention_heads': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': False, 'num_hidden_layers': 6, 'attention_window': [1024, 1024, 1024, 1024, 1024, 1024], 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 512, 'min_length': 100, 'do_sample': False, 'early_stopping': True, 'num_beams': 2, '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': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LEDForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'allenai/led-base-16384', 'transformers_version': '4.36.0', 'classif_dropout': 0.0, 'model_type': 'led', 'output_dir': './', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, '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': './runs/Jan03_10-55-16_416a3b7a3d3d', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, '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': 10, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': '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': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None}
+2024-01-03 11:04:25,631 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:04:25,631 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:08,175 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:08,177 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:08,177 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:09,557 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:09,559 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:09,559 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:09,778 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:09,785 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:09,785 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:11,278 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:11,290 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:05:11,290 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:05:12,067 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:05:12,538 INFO    MainThread:99 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 50265, 'max_encoder_position_embeddings': 16384, 'max_decoder_position_embeddings': 1024, 'd_model': 768, 'encoder_ffn_dim': 3072, 'encoder_layers': 6, 'encoder_attention_heads': 12, 'decoder_ffn_dim': 3072, 'decoder_layers': 6, 'decoder_attention_heads': 12, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': False, 'num_hidden_layers': 6, 'attention_window': [1024, 1024, 1024, 1024, 1024, 1024], 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 512, 'min_length': 100, 'do_sample': False, 'early_stopping': True, 'num_beams': 2, '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': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LEDForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'allenai/led-base-16384', 'transformers_version': '4.36.0', 'classif_dropout': 0.0, 'model_type': 'led', 'output_dir': './', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, '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': './runs/Jan03_11-05-09_416a3b7a3d3d', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, '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': 10, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': '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': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': None, 'generation_num_beams': None, 'generation_config': None}
+2024-01-03 11:27:53,766 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:27:53,766 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:28:23,468 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:28:24,109 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:28:24,109 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:29:06,752 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-03 11:29:06,779 INFO    MainThread:99 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-03 11:29:06,780 INFO    MainThread:99 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-03 11:29:56,569 INFO    MainThread:99 [wandb_init.py:_resume_backend():440] resuming backend