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 sha256:813dbac8fa97274e3b70cfab4505d0cf98217bbd3b2d9625e4c48e711f7ee71a
-size 997319877

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:326a83ac44b4cb085870abefd7a35886a46642d787bc336ef344978da0292ebb
-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": 0.49069943344752504,
-  "best_model_checkpoint": "citation_intent_classification_roberta/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": 1.4059,
-      "step": 100
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.6491228070175439,
-      "eval_f1_macro": 0.2714097496706192,
-      "eval_loss": 1.058456540107727,
-      "eval_runtime": 0.3475,
-      "eval_samples_per_second": 328.058,
-      "eval_steps_per_second": 23.022,
-      "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": 0.3442,
-      "eval_samples_per_second": 331.224,
-      "eval_steps_per_second": 23.244,
-      "step": 211
-    },
-    {
-      "epoch": 2.84,
-      "learning_rate": 1.5197568389057753e-05,
-      "loss": 0.8144,
-      "step": 300
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.7280701754385965,
-      "eval_f1_macro": 0.49069943344752504,
-      "eval_loss": 0.7686166167259216,
-      "eval_runtime": 0.3431,
-      "eval_samples_per_second": 332.269,
-      "eval_steps_per_second": 23.317,
-      "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 sha256:3b7f58cffb7d70da6a2e292c5de3ee7838417a167d657e511574610d8ef27c17
-size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326a83ac44b4cb085870abefd7a35886a46642d787bc336ef344978da0292ebb
+oid sha256:7d076d24229c602e16c71c883f056078cb1ff31bb06c0f499fe108cea3272e23
 size 498674357

runs/Apr21_00-03-56_jupyter/events.out.tfevents.1713657840.jupyter.2695507.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bc2ed98dd8117b474ebb592be0d7ef671f15d40c40af929a3fada626f3897a
-size 5939
+oid sha256:3d40559630fc16040077a16948332932cd67f1a106d66c75f86c05602c09fc55
+size 10017

last-checkpoint/scheduler.pt → runs/Apr21_00-03-56_jupyter/events.out.tfevents.1713658313.jupyter.2695507.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4404a5e593daf7e425c8a92c57bc8d6f59c6c97b64a73aae6afdd14574ef05
-size 627
+oid sha256:66df20f9ef7effd924518369f69214e23ee916b4ae040247c122e2bad8542f8d
+size 415