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:c552b5848c04a7fda896206461f261477d574ee49a71235a80e75eed081578b5
-size 997319877

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a1c945b4736395cc83849de8d5a3156b09cf02ade01c7a0d01330c70777fdb05
-size 498674357

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ca2a6098052f5420268e5519bd00e10332340078658775d4537ceb30ab71817a
-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

@@ -1,64 +0,0 @@
-{
-  "best_metric": 0.5226846644169478,
-  "best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-316",
-  "epoch": 2.995260663507109,
-  "global_step": 316,
-  "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": 0.3306,
-      "eval_samples_per_second": 344.809,
-      "eval_steps_per_second": 24.197,
-      "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": 0.328,
-      "eval_samples_per_second": 347.558,
-      "eval_steps_per_second": 24.39,
-      "step": 211
-    },
-    {
-      "epoch": 2.84,
-      "learning_rate": 1.5197568389057753e-05,
-      "loss": 0.815,
-      "step": 300
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.7719298245614035,
-      "eval_f1_macro": 0.5226846644169478,
-      "eval_loss": 0.807743489742279,
-      "eval_runtime": 0.3269,
-      "eval_samples_per_second": 348.728,
-      "eval_steps_per_second": 24.472,
-      "step": 316
-    }
-  ],
-  "max_steps": 1050,
-  "num_train_epochs": 10,
-  "total_flos": 265093908618240.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:670b3512c08338fa24d75716c6903020ba768f770e947f27df749abcaeeadfe6
-size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c945b4736395cc83849de8d5a3156b09cf02ade01c7a0d01330c70777fdb05
+oid sha256:93e843b6b1f82247cd8cc8c25e4844ad852f65161c79874e2e54554b00df441a
 size 498674357

runs/Apr21_00-03-51_jupyter/events.out.tfevents.1713657834.jupyter.2697769.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2cfa6b02d58ddf29e81fd91458d9e7fbfef25a190b8e2a439cea7b53d56ebf1
-size 5976
+oid sha256:4f740787dad33887a70e0f6d0cae5a2d1dda2ce8bed8dbecc348621904a45b18
+size 10054

last-checkpoint/scheduler.pt → runs/Apr21_00-03-51_jupyter/events.out.tfevents.1713658305.jupyter.2697769.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4404a5e593daf7e425c8a92c57bc8d6f59c6c97b64a73aae6afdd14574ef05
-size 627
+oid sha256:4c79d27517dbe7c8ffa1c8ab26a217128c5f342a5098e8ef3b8bebc1d517f45c
+size 415