Training in progress, epoch 0, checkpoint

last-checkpoint/config.json

@@ -1,51 +1,51 @@
-{
-  "_name_or_path": "uitnlp/CafeBERT",
-  "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",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8
-  },
-  "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": "4.46.3",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}
+{
+  "_name_or_path": "uitnlp/CafeBERT",
+  "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",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "4.45.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8fa60bc6a88d3c5a2b31301d88ae4dd39aa97fffbff26740ea0326eb7d2fb63
+oid sha256:ee88694ce3b4f5826fecc70211fd772035eda6bc319dbd4e755f4535eb11aaf2
 size 2239647372

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ca6d053d917506c1c353749bc45dfd03c8165e6d3287aed6111f17198f6126
+oid sha256:bffc3f94c209af4b58101446bd7d15fda797bf44b6dadc22a98da38e88a1bbb1
 size 4479530129

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce1c6841c61906294cd9f76d9e5214d674107a79d9a570a3fdd3b7b30104997
+oid sha256:96d14ca04c2f9361d2f6d84d70559a1de3fcbf07dc4c68dd538c2f9ca5f7da21
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c5eb2272c4ffb00d50566cb83815b01ea06240251cfeac8f0e527eb078d962
+oid sha256:015167d95b97f644765cc744f086d000ba31eb641587ca2854c499dcc1b9d581
 size 1064

last-checkpoint/special_tokens_map.json

@@ -1,15 +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>"
-}
+{
+  "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>"
+}

last-checkpoint/tokenizer_config.json

@@ -1,55 +1,55 @@
-{
-  "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": false,
-  "cls_token": "<s>",
-  "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>"
-}
+{
+  "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": false,
+  "cls_token": "<s>",
+  "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>"
+}

last-checkpoint/trainer_state.json

@@ -1,78 +1,42 @@
-{
-  "best_metric": 0.5109140518417462,
-  "best_model_checkpoint": "../../modelParams/TrainingArguments_output\\checkpoint-455",
-  "epoch": 4.982935153583618,
-  "eval_steps": 500,
-  "global_step": 455,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.9938566552901024,
-      "eval_accuracy": 0.42905866302864937,
-      "eval_loss": 1.574777364730835,
-      "eval_runtime": 298.6296,
-      "eval_samples_per_second": 4.909,
-      "eval_steps_per_second": 1.229,
-      "step": 91
-    },
-    {
-      "epoch": 1.9911262798634812,
-      "eval_accuracy": 0.4931787175989086,
-      "eval_loss": 1.4048564434051514,
-      "eval_runtime": 296.1396,
-      "eval_samples_per_second": 4.95,
-      "eval_steps_per_second": 1.239,
-      "step": 182
-    },
-    {
-      "epoch": 2.98839590443686,
-      "eval_accuracy": 0.5068212824010914,
-      "eval_loss": 1.3609565496444702,
-      "eval_runtime": 297.4155,
-      "eval_samples_per_second": 4.929,
-      "eval_steps_per_second": 1.234,
-      "step": 273
-    },
-    {
-      "epoch": 3.9965870307167233,
-      "eval_accuracy": 0.4979536152796726,
-      "eval_loss": 1.3629751205444336,
-      "eval_runtime": 310.5251,
-      "eval_samples_per_second": 4.721,
-      "eval_steps_per_second": 1.182,
-      "step": 365
-    },
-    {
-      "epoch": 4.982935153583618,
-      "eval_accuracy": 0.5109140518417462,
-      "eval_loss": 1.3806899785995483,
-      "eval_runtime": 322.0535,
-      "eval_samples_per_second": 4.552,
-      "eval_steps_per_second": 1.14,
-      "step": 455
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 455,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 2.713848315150336e+16,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}
+{
+  "best_metric": 0.4631650750341064,
+  "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-45",
+  "epoch": 0.9822646657571623,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9822646657571623,
+      "eval_accuracy": 0.4631650750341064,
+      "eval_loss": 1.5760536193847656,
+      "eval_runtime": 39.2455,
+      "eval_samples_per_second": 37.355,
+      "eval_steps_per_second": 4.688,
+      "step": 45
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2719956978484200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d95b1b80f6ab7edaa3c7b16e0baaf8e805120a6315b621d90e9d095a86d084
-size 5368
+oid sha256:a68a9403af5b179e3b07610e3bdc2f379f943c6b6adf68d8636afeed754a7b70
+size 5304