Training in progress, epoch 0

last-checkpoint/config.json

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f11c590e1480fdf74fe4b6544fd70a709a2fdeff7ceaa9f956963ba6391b693
+size 997319621

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49e7f97df5d0c52c5d427c6593efb44759e13cc4ef9a15b734b007a931c1603
+size 498674357

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c35b1ae88be42b3fc92099950abfbbe324644492e7989ad94dbaa43aedacea0
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be33b98103a754b8daaa7225a843cc0a81e2ebb32ec4f7e3413258e9dc61582
+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 +1,26 @@
+{
+  "best_metric": 0.11368015414258188,
+  "best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-26",
+  "epoch": 0.9811320754716981,
+  "global_step": 26,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.5175438596491229,
+      "eval_f1_macro": 0.11368015414258188,
+      "eval_loss": 1.3259084224700928,
+      "eval_runtime": 0.2373,
+      "eval_samples_per_second": 480.486,
+      "eval_steps_per_second": 8.43,
+      "step": 26
+    }
+  ],
+  "max_steps": 260,
+  "num_train_epochs": 10,
+  "total_flos": 123604968402720.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850dcbf530c8746562c3ed0c901615bb744f72e33001f57218d77bd21d67f432
+size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41da091a0a5615d42ed01cb1114802593023b927e6691850167b888fec50d86c
+oid sha256:f49e7f97df5d0c52c5d427c6593efb44759e13cc4ef9a15b734b007a931c1603
 size 498674357

runs/Apr20_23-26-32_jupyter/events.out.tfevents.1713655596.jupyter.2682803.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb4c5581a508c48a792286e0811aaaeedfea2db3d5a4c15ccff8c6fa065ad52
+size 4721

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344e3b115407a6420c5475134dc85aa4f4bbb53619400023ae7459cf9a3b2394
+oid sha256:850dcbf530c8746562c3ed0c901615bb744f72e33001f57218d77bd21d67f432
 size 4027