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:e5c01506ef657a5cfe82e6d5c93387b32d58a71063bbbb9197676d07bc9df237
-size 997319877

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6168d3ea6ea415ac5d4b8f9268699d58544bd98aa79aeabeb94e0511fee359c9
-size 498674357

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b13cc8b183bab9e3f2965176c88613417f4bdc40431893a4eaf37d5e24d0725c
-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

@@ -1,80 +0,0 @@
-{
-  "best_metric": 0.5226846644169478,
-  "best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-316",
-  "epoch": 4.0,
-  "global_step": 422,
-  "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": 0.3349,
-      "eval_samples_per_second": 340.352,
-      "eval_steps_per_second": 23.884,
-      "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": 0.3307,
-      "eval_samples_per_second": 344.743,
-      "eval_steps_per_second": 24.193,
-      "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": 0.3274,
-      "eval_samples_per_second": 348.195,
-      "eval_steps_per_second": 24.435,
-      "step": 316
-    },
-    {
-      "epoch": 3.79,
-      "learning_rate": 1.3171225937183386e-05,
-      "loss": 0.5604,
-      "step": 400
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.7280701754385965,
-      "eval_f1_macro": 0.4904761087856539,
-      "eval_loss": 0.7902174592018127,
-      "eval_runtime": 0.3258,
-      "eval_samples_per_second": 349.926,
-      "eval_steps_per_second": 24.556,
-      "step": 422
-    }
-  ],
-  "max_steps": 1050,
-  "num_train_epochs": 10,
-  "total_flos": 352832263206048.0,
-  "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:fb84a00c5010b90fdb2212534c247d502558e498d897046cbf48bcdf1d65fa0b
-size 4027

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6168d3ea6ea415ac5d4b8f9268699d58544bd98aa79aeabeb94e0511fee359c9
+oid sha256:93e843b6b1f82247cd8cc8c25e4844ad852f65161c79874e2e54554b00df441a
 size 498674357

runs/Apr21_00-12-24_jupyter/events.out.tfevents.1713658348.jupyter.2697769.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6064aa032d50f348e614df9ee886e98d34a553451b0b79cf457a82c25c181e76
-size 6508
+oid sha256:939570fe2fffd8cc739cf9dab88a610eeab32f5142492e02b60ad2d3eafdfee4
+size 10054

last-checkpoint/scheduler.pt → runs/Apr21_00-12-24_jupyter/events.out.tfevents.1713658951.jupyter.2697769.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d93a7f55b88f81f3a8daa77a3fd516f0eb2469d9d57b82f0d4c87ab8988d61ea
-size 627
+oid sha256:25a199548a3e393d6f5e0f92fa2c663d6433f131bacda270cfc0973db924458b
+size 415