Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+best_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3515-epoch-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

best_model/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

best_model/eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 0.5814772625764211
+macro_f1 = 0.7436809577572236
+mcc = 0.5966666048090462
+weighted_f1 = 0.7324417656265867

best_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13105720132ec03ebfd4eb5508b796b7c5f8b1f0f9e84d62ed3793921f0c223
+size 2239622772

best_model/model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/sentiment_analysis/xlm-roberta-large/best_model", "cache_dir": "cache_dir/sentiment_analysis/xlm-roberta-large", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 200, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/sentiment_analysis/xlm-roberta-large", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 200, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "FacebookAI/xlm-roberta-large", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "FacebookAI/xlm-roberta-large"}, "wandb_project": "Sinhala Sentiment Analysis", "warmup_ratio": 0.06, "warmup_steps": 211, "weight_decay": 0.0, "model_class": "TextClassificationModel", "labels_list": ["NEUTRAL", "POSITIVE", "NEGATIVE"], "labels_map": {"NEUTRAL": 0, "POSITIVE": 1, "NEGATIVE": 2}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

best_model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9900937ab99c54588c881b7f28dbb5b9a57a7f43eb25dfe8c981fef16e4b29b7
+size 4479480913

best_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f585df97668b93c326e516f34bcc448ad5e31413fd676452bf4cf5ee1f62db86
+size 1064

best_model/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

best_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f76fe13d42f80dcee0cb86a1aeb5f14f8909bb8a8782f7a4a4ad76697ef164
+size 17083021

best_model/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee53ce38797d6ec6b99e3ad3d26223e23bb26b405641659d2ffda10da0ab4f0d
+size 3896

checkpoint-3515-epoch-5/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-3515-epoch-5/eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 1.248837043469151
+macro_f1 = 0.754510368400943
+mcc = 0.6091355890255944
+weighted_f1 = 0.7467623636936299

checkpoint-3515-epoch-5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a177958585cfbc30211688cca0af9e24a1af9daaaaf7426f4bcf627a9b0fe86d
+size 2239622772

checkpoint-3515-epoch-5/model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/sentiment_analysis/xlm-roberta-large/best_model", "cache_dir": "cache_dir/sentiment_analysis/xlm-roberta-large", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 200, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/sentiment_analysis/xlm-roberta-large", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 200, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "FacebookAI/xlm-roberta-large", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "FacebookAI/xlm-roberta-large"}, "wandb_project": "Sinhala Sentiment Analysis", "warmup_ratio": 0.06, "warmup_steps": 211, "weight_decay": 0.0, "model_class": "TextClassificationModel", "labels_list": ["NEUTRAL", "POSITIVE", "NEGATIVE"], "labels_map": {"NEUTRAL": 0, "POSITIVE": 1, "NEGATIVE": 2}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

checkpoint-3515-epoch-5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956d51b8c6f4b717fa270148189d0e263dbd2ec000b68c28c1ff0206979c65c5
+size 4479480913

checkpoint-3515-epoch-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b228755c296ba433f15c642a85eaefdc12ec36ec8541c9ecba3e16923b81de98
+size 1064

checkpoint-3515-epoch-5/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-3515-epoch-5/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f76fe13d42f80dcee0cb86a1aeb5f14f8909bb8a8782f7a4a4ad76697ef164
+size 17083021

checkpoint-3515-epoch-5/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-3515-epoch-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee53ce38797d6ec6b99e3ad3d26223e23bb26b405641659d2ffda10da0ab4f0d
+size 3896

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 1.248837043469151
+macro_f1 = 0.754510368400943
+mcc = 0.6091355890255944
+weighted_f1 = 0.7467623636936299

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a177958585cfbc30211688cca0af9e24a1af9daaaaf7426f4bcf627a9b0fe86d
+size 2239622772

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/sentiment_analysis/xlm-roberta-large/best_model", "cache_dir": "cache_dir/sentiment_analysis/xlm-roberta-large", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 200, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/sentiment_analysis/xlm-roberta-large", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 200, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "FacebookAI/xlm-roberta-large", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "FacebookAI/xlm-roberta-large"}, "wandb_project": "Sinhala Sentiment Analysis", "warmup_ratio": 0.06, "warmup_steps": 211, "weight_decay": 0.0, "model_class": "TextClassificationModel", "labels_list": ["NEUTRAL", "POSITIVE", "NEGATIVE"], "labels_map": {"NEUTRAL": 0, "POSITIVE": 1, "NEGATIVE": 2}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f76fe13d42f80dcee0cb86a1aeb5f14f8909bb8a8782f7a4a4ad76697ef164
+size 17083021

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee53ce38797d6ec6b99e3ad3d26223e23bb26b405641659d2ffda10da0ab4f0d
+size 3896

training_progress_scores.csv

@@ -0,0 +1,23 @@
+global_step,train_loss,mcc,macro_f1,weighted_f1,eval_loss
+200,1.2740478515625,0.0,0.20908646800195407,0.28661959955285665,1.0856874982515972
+400,1.12109375,0.45370527857806,0.5069396518671881,0.5327143438392085,0.7363095263640086
+600,0.755615234375,0.559410053459283,0.7229230786961027,0.7182287251838261,0.6309637506802876
+703,0.6925455927848816,0.5841254861560833,0.7417131419133031,0.7368815353141769,0.6001911779244741
+800,0.9465847015380859,0.5749814241055029,0.7138768330246924,0.716505697954929,0.6297397255897522
+1000,0.7311162948608398,0.5765328705516929,0.7214251289757603,0.7197448775744766,0.6152580499649047
+1200,1.0870819091796875,0.5927925342739295,0.7385061306938554,0.7378861511708116,0.5998952746391296
+1400,0.46545839309692383,0.5966666048090462,0.7436809577572236,0.7324417656265867,0.5814772625764211
+1406,0.08297475427389145,0.5856962389317353,0.734241968440681,0.7206046007797268,0.6061947524547577
+1600,0.9884705543518066,0.5923899360096098,0.7413628155233102,0.7362828234852306,0.7091383437315623
+1800,0.2916221618652344,0.6109092522386388,0.7553873600177446,0.7490238492101229,0.6481002926826477
+2000,0.14180994033813477,0.6052498069846522,0.7517248545505063,0.7488353437867608,0.6463229954242706
+2109,1.0794576406478882,0.6073081908660072,0.7449988048184228,0.744446632106959,0.6494138618310292
+2200,0.05569934844970703,0.5962711346331006,0.7387821003394642,0.7345038420699701,0.9018320540587107
+2400,0.005150020122528076,0.6141352412030552,0.7556020427259549,0.7483705747798095,0.9655490010976792
+2600,0.49518153071403503,0.5987241870436524,0.7478071465398726,0.7400133249895322,1.0073274970054626
+2800,0.24290084838867188,0.6088688838403056,0.7521436261690712,0.7456648548013942,0.9630749734739462
+2812,1.9715728759765625,0.6112395214732101,0.7532529004354768,0.7457280368021947,0.991997197518746
+3000,0.1175423264503479,0.6092184473077218,0.7519714722363728,0.7468428996941642,1.1885264371832212
+3200,0.0014830827713012695,0.6121447348298368,0.757150461791023,0.7502511022015914,1.202283516774575
+3400,0.002510964870452881,0.6109976732339154,0.755641881917235,0.7481495655392887,1.2439544717470805
+3515,0.01666259765625,0.6091355890255944,0.754510368400943,0.7467623636936299,1.248837043469151