citation_intent_classification_roberta

last-checkpoint/config.json

@@ -1,45 +0,0 @@
-{
-  "_name_or_path": "roberta-base",
-  "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:d368d077a0f444a0992c017207945d7447e79b57de30f24df1bd30ac7d4e58cf
-size 997319621

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:757180f5847e6e6e8adc313dea5ce34782c19436414b11183013431c12c89f61
-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": 0.32540006346615896,
-  "best_model_checkpoint": "citation_intent_classification_roberta/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": 1.4059,
-      "step": 100
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.6491228070175439,
-      "eval_f1_macro": 0.2714097496706192,
-      "eval_loss": 1.058456540107727,
-      "eval_runtime": 0.3456,
-      "eval_samples_per_second": 329.861,
-      "eval_steps_per_second": 23.148,
-      "step": 105
-    },
-    {
-      "epoch": 1.9,
-      "learning_rate": 1.7223910840932118e-05,
-      "loss": 1.0405,
-      "step": 200
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.6842105263157895,
-      "eval_f1_macro": 0.32540006346615896,
-      "eval_loss": 0.9257992506027222,
-      "eval_runtime": 0.3473,
-      "eval_samples_per_second": 328.201,
-      "eval_steps_per_second": 23.032,
-      "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:dc6dd7fc3e3b01a33af39bbfe820fb6c0b33376ba57f49fcf65dd3f40bf8aff8
-size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757180f5847e6e6e8adc313dea5ce34782c19436414b11183013431c12c89f61
+oid sha256:7d076d24229c602e16c71c883f056078cb1ff31bb06c0f499fe108cea3272e23
 size 498674357

runs/Apr20_23-56-38_jupyter/events.out.tfevents.1713657402.jupyter.2695507.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d656c80c2e480e10e021e9249c6e707aa6cb23ea8b0e70d0f93bf74508986d6b
-size 5407
+oid sha256:5c7b5049bed22e718f07e83cbc84e8ef74d52bb335c2340be4a3b30545ed2abe
+size 10017

last-checkpoint/scheduler.pt → runs/Apr20_23-56-38_jupyter/events.out.tfevents.1713657789.jupyter.2695507.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8630ed6b65e3550515505b33e335b0d86561e79d9eaa57ead62028ad30608d0e
-size 627
+oid sha256:686c60ddf72c2c76bf0238e7bf1faf5d0592ac9b341d3abbb51e4679bdb7d32a
+size 415