Training in progress, epoch 0

last-checkpoint/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "ltuzova/cs_domain_pretrained_model",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Background",
+    "1": "CompareOrContrast",
+    "2": "Uses",
+    "3": "Motivation",
+    "4": "Future",
+    "5": "Extends"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Background": 0,
+    "CompareOrContrast": 1,
+    "Extends": 5,
+    "Future": 4,
+    "Motivation": 3,
+    "Uses": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_of_labels": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3773a4792c35fd89732bc0cf349c3345a51037736b683ea70afd493bb4b73053
+size 997319621

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3f2c5b83d8a4a2bde35b3c81988d7dc8e467912ba86dd8ea0b252c18b51f68
+size 498674357

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e7f2bd676c936e7a6fdf9cde6071c5938c578820d54a54ab03298d96dc82c2
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6aae226b0a385b18c8012f4d652e8fbdd18f15a3fe78c710dfd63cccbeb8c1b
+size 627

last-checkpoint/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>"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": 0.24471943248844252,
+  "best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-105",
+  "epoch": 0.995260663507109,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.9250253292806485e-05,
+      "loss": 1.4387,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6140350877192983,
+      "eval_f1_macro": 0.24471943248844252,
+      "eval_loss": 1.0765323638916016,
+      "eval_runtime": 0.3327,
+      "eval_samples_per_second": 342.634,
+      "eval_steps_per_second": 24.044,
+      "step": 105
+    }
+  ],
+  "max_steps": 1050,
+  "num_train_epochs": 10,
+  "total_flos": 88083700250400.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc910e283050f49129150e31f17fdf803167d2bd63b2e5fae3edaa9a84ca5c6
+size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07d93a87c4e2ff39ff6d37e3978096ba0f2244c1339460e4dff4ce416948d22
+oid sha256:bc3f2c5b83d8a4a2bde35b3c81988d7dc8e467912ba86dd8ea0b252c18b51f68
 size 498674357

runs/Apr20_23-51-29_jupyter/events.out.tfevents.1713657093.jupyter.2697769.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d7131fe512b3f60ff1922bf0d5e10b760c4aeed2d879ff6bf66dfeb8c8fed4
+size 4912

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82ba2d5725c467bfc3412179472a4ca7b1afb1409e3c26c41d2afbb8ac6165b
+oid sha256:6cc910e283050f49129150e31f17fdf803167d2bd63b2e5fae3edaa9a84ca5c6
 size 4027