citation_intent_classification_roberta_dapt

last-checkpoint/config.json

@@ -1,45 +0,0 @@
-{
-  "_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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:53267e287e87678ed1b99c9cb37eaa0b31913145e60c1a91d94cf7e8a67f257f
-size 997319621

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd91baae36f607e5321af3a053f96ac16074130338a97959884c93a263756ea4
-size 498674357

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:190ec63f1eff039dd063347cda3f4ca17867f19ff6206e72f252578f29b0a5aa
-size 14575

last-checkpoint/special_tokens_map.json

@@ -1,15 +0,0 @@
-{
-  "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

@@ -1,15 +0,0 @@
-{
-  "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

@@ -1,48 +0,0 @@
-{
-  "best_metric": 0.34632500717772036,
-  "best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-211",
-  "epoch": 2.0,
-  "global_step": 211,
-  "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": 0.3339,
-      "eval_samples_per_second": 341.409,
-      "eval_steps_per_second": 23.959,
-      "step": 105
-    },
-    {
-      "epoch": 1.9,
-      "learning_rate": 1.7223910840932118e-05,
-      "loss": 1.0272,
-      "step": 200
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.7192982456140351,
-      "eval_f1_macro": 0.34632500717772036,
-      "eval_loss": 0.881606936454773,
-      "eval_runtime": 0.33,
-      "eval_samples_per_second": 345.427,
-      "eval_steps_per_second": 24.24,
-      "step": 211
-    }
-  ],
-  "max_steps": 1050,
-  "num_train_epochs": 10,
-  "total_flos": 177618674535264.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e0794e564fade6744685eb21c793c786fec61d24890011206940a2b45f78f3d
-size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd91baae36f607e5321af3a053f96ac16074130338a97959884c93a263756ea4
+oid sha256:93e843b6b1f82247cd8cc8c25e4844ad852f65161c79874e2e54554b00df441a
 size 498674357

runs/Apr20_23-56-57_jupyter/events.out.tfevents.1713657420.jupyter.2697769.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79330363abc72a67451bfaff6be6db8b8364157fb32a0db12907f9a27a1b2a5
-size 5444
+oid sha256:f09c913cd0a7d6861860716b3cb13319947f198665813d3d39f6dde04b08a459
+size 10054

last-checkpoint/scheduler.pt → runs/Apr20_23-56-57_jupyter/events.out.tfevents.1713657787.jupyter.2697769.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8630ed6b65e3550515505b33e335b0d86561e79d9eaa57ead62028ad30608d0e
-size 627
+oid sha256:59fcfff2cebdba209b339d77c82f1b6e4ad9c120eafa479c9a3d6246c626f0c1
+size 415