tharindu commited on Mar 19

Commit

d8986d0

•

1 Parent(s): 8bce57f

Upload folder using huggingface_hub

Browse files

Files changed (29) hide show

best_model/config.json +40 -0
best_model/eval_results.txt +4 -0
best_model/model.safetensors +3 -0
best_model/model_args.json +1 -0
best_model/optimizer.pt +3 -0
best_model/scheduler.pt +3 -0
best_model/sentencepiece.bpe.model +3 -0
best_model/special_tokens_map.json +15 -0
best_model/tokenizer_config.json +56 -0
best_model/training_args.bin +3 -0
checkpoint-8725-epoch-5/config.json +40 -0
checkpoint-8725-epoch-5/eval_results.txt +4 -0
checkpoint-8725-epoch-5/model.safetensors +3 -0
checkpoint-8725-epoch-5/model_args.json +1 -0
checkpoint-8725-epoch-5/optimizer.pt +3 -0
checkpoint-8725-epoch-5/scheduler.pt +3 -0
checkpoint-8725-epoch-5/sentencepiece.bpe.model +3 -0
checkpoint-8725-epoch-5/special_tokens_map.json +15 -0
checkpoint-8725-epoch-5/tokenizer_config.json +56 -0
checkpoint-8725-epoch-5/training_args.bin +3 -0
config.json +40 -0
eval_results.txt +4 -0
model.safetensors +3 -0
model_args.json +1 -0
sentencepiece.bpe.model +3 -0
special_tokens_map.json +15 -0
tokenizer_config.json +56 -0
training_args.bin +3 -0
training_progress_scores.csv +20 -0

best_model/config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

best_model/eval_results.txt ADDED Viewed

	@@ -0,0 +1,4 @@

+eval_loss = 0.22451437553198836
+macro_f1 = 0.9418695660786534
+mcc = 0.9231774868008514
+weighted_f1 = 0.9418627152197988

best_model/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:577cc8da5ec9ce385adcf449427a6de57a5d7d5847c0c936e80ee64770b539db
+size 1114573728

best_model/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-base/best_model", "cache_dir": "cache_dir/xlm-roberta-base", "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": 3, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 600, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 600, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-base", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/xlm-roberta-base", "overwrite_output_dir": true, "process_count": 78, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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": 600, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": "NSINa_category_prediction", "warmup_ratio": 0.06, "warmup_steps": 524, "weight_decay": 0.0, "model_class": "LCPModel", "labels_list": [0, 1, 2, 3], "labels_map": {}, "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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b48cfdcc57475966d8dffab143840c664bb853b94e86b892208dc37648524f5b
+size 2224492154

best_model/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1363d6a0d432da05838bdce5582f1234621184236a0c7c47bf959ae3ef7b3aac
+size 1064

best_model/sentencepiece.bpe.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

best_model/special_tokens_map.json ADDED Viewed

	@@ -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_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "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>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

best_model/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1403e2ea200a15eb7df640a1bc2a3b44e3b61377974714b32c90fecc583cde6
+size 3576

checkpoint-8725-epoch-5/config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-8725-epoch-5/eval_results.txt ADDED Viewed

	@@ -0,0 +1,4 @@

+eval_loss = 0.3184521266471681
+macro_f1 = 0.9422464561950047
+mcc = 0.9237257971341494
+weighted_f1 = 0.9422630573465308

checkpoint-8725-epoch-5/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60d7021afe4c23384999a95e388364be98bb961f42a43d3ac72d667b82555e9
+size 1114573728

checkpoint-8725-epoch-5/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-8725-epoch-5/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:580238bdb4410a4b69545e40387b7bb04a333a394fbf8cd7f1be6624a6e6d35b
+size 2224492154

checkpoint-8725-epoch-5/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:faf3b20aae09053b469f456c0a1ae63775158cccfb279532733245f8dd12b35b
+size 1064

checkpoint-8725-epoch-5/sentencepiece.bpe.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

checkpoint-8725-epoch-5/special_tokens_map.json ADDED Viewed

	@@ -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-8725-epoch-5/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "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>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-8725-epoch-5/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1403e2ea200a15eb7df640a1bc2a3b44e3b61377974714b32c90fecc583cde6
+size 3576

config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt ADDED Viewed

	@@ -0,0 +1,4 @@

+eval_loss = 0.3184521266471681
+macro_f1 = 0.9422464561950047
+mcc = 0.9237257971341494
+weighted_f1 = 0.9422630573465308

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60d7021afe4c23384999a95e388364be98bb961f42a43d3ac72d667b82555e9
+size 1114573728

model_args.json ADDED Viewed

	@@ -0,0 +1 @@

sentencepiece.bpe.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json ADDED Viewed

	@@ -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_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "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>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1403e2ea200a15eb7df640a1bc2a3b44e3b61377974714b32c90fecc583cde6
+size 3576

training_progress_scores.csv ADDED Viewed

	@@ -0,0 +1,20 @@

+global_step,mcc,train_loss,eval_loss,macro_f1,weighted_f1
+600,0.8658420105987815,0.17037677764892578,0.3978164923406139,0.8980346282091274,0.8983274982055817
+1200,0.9043286560841602,0.23795676231384277,0.2500070985790688,0.9269870015500248,0.9270863231166491
+1745,0.9077794718154207,0.2868804931640625,0.2319631111836925,0.9289583951957032,0.9291332069934942
+1800,0.9101884387025756,0.31981027126312256,0.27001249709541036,0.9309137889403055,0.9311214953190751
+2400,0.9123765136862189,0.33961236476898193,0.263530822682012,0.9329487721060283,0.9331683787177707
+3000,0.9142204697266915,0.016527652740478516,0.23452939880416565,0.9337464787655964,0.9336878295450092
+3490,0.9082759135953719,0.7253953814506531,0.24121883178379425,0.9300762491819153,0.9304015574212304
+3600,0.9231774868008514,0.501331090927124,0.22451437553198836,0.9418695660786534,0.9418627152197988
+4200,0.9175011574489094,0.28461983799934387,0.25145731425181644,0.9372121078270728,0.937078839767871
+4800,0.9214334024446419,0.008817285299301147,0.2521561642931102,0.9402539793244773,0.9401193094754979
+5235,0.9197526360842831,0.41614019870758057,0.2526795017657821,0.9389884395980652,0.9388384147763035
+5400,0.9255631817382479,0.012829333543777466,0.25080774236259235,0.9431167331332937,0.9430081865883545
+6000,0.9222669515194348,0.002891242504119873,0.277265720355046,0.940749455580705,0.9407164009335942
+6600,0.9185874703943337,0.001784205436706543,0.3044330812714629,0.9379388469170568,0.9380046570314617
+6980,0.9211445094317083,0.0020355312153697014,0.2959481056157941,0.93977819567623,0.9397649376840287
+7200,0.9251780148668602,0.002990923821926117,0.2966543456459101,0.943195402238173,0.9431148002405392
+7800,0.9202797033417398,0.3372035026550293,0.32210758333898526,0.9396843215731252,0.9396223981580855
+8400,0.9219589450365042,0.0009760484099388123,0.3200311442403862,0.9409985496479418,0.9409977480787901
+8725,0.9237257971341494,0.0022705034352838993,0.3184521266471681,0.9422464561950047,0.9422630573465308