Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "./results/Entity_Action",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896acd461faa67488cd14bc0fd13c2328e196de5796aadc582f0569e30c0dd3e
+size 567598552

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_log.txt

@@ -0,0 +1,160 @@
+Input data filename: project-30-at-2024-08-27-13-17-2b8a675a_ind_theme_split_27_aug_andtitledescr.json
+Training date and time: 2024-08-27 14:57:34.590724
+
+Training parameters:
+output_dir: ./results/Entity_Action
+overwrite_output_dir: False
+do_train: False
+do_eval: True
+do_predict: False
+eval_strategy: epoch
+prediction_loss_only: False
+per_device_train_batch_size: 8
+per_device_eval_batch_size: 8
+per_gpu_train_batch_size: None
+per_gpu_eval_batch_size: None
+gradient_accumulation_steps: 1
+eval_accumulation_steps: None
+eval_delay: 0
+learning_rate: 4.270726644478662e-05
+weight_decay: 0.21946446535298075
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1e-08
+max_grad_norm: 1.0
+num_train_epochs: 5
+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: ./logs
+logging_strategy: epoch
+logging_first_step: False
+logging_steps: 10
+logging_nan_inf_filter: True
+save_strategy: epoch
+save_steps: 500
+save_total_limit: None
+save_safetensors: True
+save_on_each_node: False
+save_only_model: False
+restore_callback_states_from_checkpoint: False
+no_cuda: False
+use_cpu: False
+use_mps_device: False
+seed: 42
+data_seed: None
+jit_mode_eval: False
+use_ipex: False
+bf16: False
+fp16: False
+fp16_opt_level: O1
+half_precision_backend: auto
+bf16_full_eval: False
+fp16_full_eval: False
+tf32: None
+local_rank: 0
+ddp_backend: None
+tpu_num_cores: None
+tpu_metrics_debug: False
+debug: []
+dataloader_drop_last: False
+eval_steps: None
+dataloader_num_workers: 0
+dataloader_prefetch_factor: None
+past_index: -1
+run_name: ./results/Entity_Action
+disable_tqdm: False
+remove_unused_columns: False
+label_names: None
+load_best_model_at_end: True
+metric_for_best_model: eval_accuracy
+greater_is_better: True
+ignore_data_skip: False
+fsdp: []
+fsdp_min_num_params: 0
+fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+fsdp_transformer_layer_cls_to_wrap: None
+accelerator_config: AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)
+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']
+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: None
+hub_private_repo: False
+hub_always_push: False
+gradient_checkpointing: False
+gradient_checkpointing_kwargs: None
+include_inputs_for_metrics: False
+eval_do_concat_batches: True
+fp16_backend: auto
+evaluation_strategy: None
+push_to_hub_model_id: None
+push_to_hub_organization: None
+push_to_hub_token: None
+mp_parameters: 
+auto_find_batch_size: False
+full_determinism: False
+torchdynamo: None
+ray_scope: last
+ddp_timeout: 1800
+torch_compile: False
+torch_compile_backend: None
+torch_compile_mode: None
+dispatch_batches: None
+split_batches: None
+include_tokens_per_second: False
+include_num_input_tokens_seen: False
+neftune_noise_alpha: None
+optim_target_modules: None
+batch_eval_metrics: False
+eval_on_start: False
+distributed_state: Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cuda
+
+_n_gpu: 1
+__cached__setup_devices: cuda:0
+deepspeed_plugin: None
+
+Best Hyperparameters:
+learning_rate: 4.270726644478662e-05
+num_train_epochs: 5
+weight_decay: 0.21946446535298075
+
+Training metrics:
+train_runtime: 672.3301
+train_samples_per_second: 18.414
+train_steps_per_second: 2.305
+total_flos: 1640004811530240.0
+train_loss: 0.12886674880981444
+epoch: 5.0
+
+All Epoch Metrics:
+Epoch	Training Loss	Validation Loss	Accuracy	Precision	Recall	F1	Bce Loss	Runtime	Samples Per Second	Steps Per Second
+1.0	0.3189	0.1607036143541336	0.9532258064516129	0.9599056603773585	0.9713603818615751	0.9655990510083036	0.16070359953727179	672.3301	18.414	2.305
+2.0	0.1528	0.11495514214038849	0.9725806451612903	0.9808612440191388	0.9785202863961814	0.9796893667861409	0.1149551347974206	672.3301	18.414	2.305
+3.0	0.0751	0.10520578175783157	0.9790322580645161	0.981042654028436	0.9880668257756563	0.9845422116527943	0.10520577938253993	672.3301	18.414	2.305
+4.0	0.0623	0.08832962810993195	0.9854838709677419	0.9904306220095693	0.9880668257756563	0.9892473118279569	0.08832962441818693	672.3301	18.414	2.305
+5.0	0.0353	0.08785796910524368	0.9838709677419355	0.9904076738609112	0.9856801909307876	0.9880382775119617	0.08785795159062294	672.3301	18.414	2.305