citation_intent_classification_roberta
Browse files- last-checkpoint/config.json +0 -45
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/special_tokens_map.json +0 -15
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -15
- last-checkpoint/trainer_state.json +0 -36
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.json +0 -0
- pytorch_model.bin +1 -1
- runs/Apr20_23-26-32_jupyter/events.out.tfevents.1713655596.jupyter.2682803.4 +2 -2
- last-checkpoint/scheduler.pt → runs/Apr20_23-26-32_jupyter/events.out.tfevents.1713655907.jupyter.2682803.5 +2 -2
last-checkpoint/config.json
DELETED
|
@@ -1,45 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "roberta-base",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"RobertaForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
-
"classifier_dropout": 0.1,
|
| 9 |
-
"eos_token_id": 2,
|
| 10 |
-
"hidden_act": "gelu",
|
| 11 |
-
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size": 768,
|
| 13 |
-
"id2label": {
|
| 14 |
-
"0": "Background",
|
| 15 |
-
"1": "CompareOrContrast",
|
| 16 |
-
"2": "Uses",
|
| 17 |
-
"3": "Motivation",
|
| 18 |
-
"4": "Future",
|
| 19 |
-
"5": "Extends"
|
| 20 |
-
},
|
| 21 |
-
"initializer_range": 0.02,
|
| 22 |
-
"intermediate_size": 3072,
|
| 23 |
-
"label2id": {
|
| 24 |
-
"Background": 0,
|
| 25 |
-
"CompareOrContrast": 1,
|
| 26 |
-
"Extends": 5,
|
| 27 |
-
"Future": 4,
|
| 28 |
-
"Motivation": 3,
|
| 29 |
-
"Uses": 2
|
| 30 |
-
},
|
| 31 |
-
"layer_norm_eps": 1e-05,
|
| 32 |
-
"max_position_embeddings": 514,
|
| 33 |
-
"model_type": "roberta",
|
| 34 |
-
"num_attention_heads": 12,
|
| 35 |
-
"num_hidden_layers": 12,
|
| 36 |
-
"num_of_labels": 6,
|
| 37 |
-
"pad_token_id": 1,
|
| 38 |
-
"position_embedding_type": "absolute",
|
| 39 |
-
"problem_type": "single_label_classification",
|
| 40 |
-
"torch_dtype": "float32",
|
| 41 |
-
"transformers_version": "4.30.2",
|
| 42 |
-
"type_vocab_size": 1,
|
| 43 |
-
"use_cache": true,
|
| 44 |
-
"vocab_size": 50265
|
| 45 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3cd58ef69f68cf2bc7e93abf0a25e693c4132ed9da30a6edafca3c0726f1205e
|
| 3 |
-
size 997319621
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:71f5ba31c406a1d0c79c4783e74ff3f69946797243fbf071ddeb80f9ac12377a
|
| 3 |
-
size 498674357
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:df5cba4ac44db0d3e6653c437413c02769b5973e7c6982f3f6a7abb3cbdbf677
|
| 3 |
-
size 14575
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"cls_token": "<s>",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"mask_token": {
|
| 6 |
-
"content": "<mask>",
|
| 7 |
-
"lstrip": true,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
-
"pad_token": "<pad>",
|
| 13 |
-
"sep_token": "</s>",
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<s>",
|
| 4 |
-
"clean_up_tokenization_spaces": true,
|
| 5 |
-
"cls_token": "<s>",
|
| 6 |
-
"eos_token": "</s>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"mask_token": "<mask>",
|
| 9 |
-
"model_max_length": 512,
|
| 10 |
-
"pad_token": "<pad>",
|
| 11 |
-
"sep_token": "</s>",
|
| 12 |
-
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
-
"trim_offsets": true,
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": 0.24786565343840886,
|
| 3 |
-
"best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-53",
|
| 4 |
-
"epoch": 2.0,
|
| 5 |
-
"global_step": 53,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.98,
|
| 12 |
-
"eval_accuracy": 0.5175438596491229,
|
| 13 |
-
"eval_f1_macro": 0.11368015414258188,
|
| 14 |
-
"eval_loss": 1.3259084224700928,
|
| 15 |
-
"eval_runtime": 0.2373,
|
| 16 |
-
"eval_samples_per_second": 480.486,
|
| 17 |
-
"eval_steps_per_second": 8.43,
|
| 18 |
-
"step": 26
|
| 19 |
-
},
|
| 20 |
-
{
|
| 21 |
-
"epoch": 2.0,
|
| 22 |
-
"eval_accuracy": 0.6228070175438597,
|
| 23 |
-
"eval_f1_macro": 0.24786565343840886,
|
| 24 |
-
"eval_loss": 1.1130008697509766,
|
| 25 |
-
"eval_runtime": 0.2398,
|
| 26 |
-
"eval_samples_per_second": 475.328,
|
| 27 |
-
"eval_steps_per_second": 8.339,
|
| 28 |
-
"step": 53
|
| 29 |
-
}
|
| 30 |
-
],
|
| 31 |
-
"max_steps": 260,
|
| 32 |
-
"num_train_epochs": 10,
|
| 33 |
-
"total_flos": 248854439960640.0,
|
| 34 |
-
"trial_name": null,
|
| 35 |
-
"trial_params": null
|
| 36 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:850dcbf530c8746562c3ed0c901615bb744f72e33001f57218d77bd21d67f432
|
| 3 |
-
size 4027
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498674357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41da091a0a5615d42ed01cb1114802593023b927e6691850167b888fec50d86c
|
| 3 |
size 498674357
|
runs/Apr20_23-26-32_jupyter/events.out.tfevents.1713655596.jupyter.2682803.4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae13ba9e542b7c5e71010b56370d008cb6ce12f1744110cc061f6720161fff28
|
| 3 |
+
size 8740
|
last-checkpoint/scheduler.pt → runs/Apr20_23-26-32_jupyter/events.out.tfevents.1713655907.jupyter.2682803.5
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f21aa78188eecafc66f09947a0d74fb1a4038afb6908d519e6fbb74ac13819d
|
| 3 |
+
size 415
|