Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-705/config.json +42 -0
- checkpoint-705/model.safetensors +3 -0
- checkpoint-705/optimizer.pt +3 -0
- checkpoint-705/rng_state.pth +3 -0
- checkpoint-705/scheduler.pt +3 -0
- checkpoint-705/trainer_state.json +832 -0
- checkpoint-705/training_args.bin +3 -0
- config.json +42 -0
- model.safetensors +3 -0
- runs/Jan19_13-42-52_r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3/events.out.tfevents.1737294174.r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3.158.0 +2 -2
- runs/Jan19_13-42-52_r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3/events.out.tfevents.1737301796.r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3.158.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: google-bert/bert-base-uncased
|
| 7 |
+
widget:
|
| 8 |
+
- text: "I love AutoTrain"
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Trained Using AutoTrain
|
| 12 |
+
|
| 13 |
+
- Problem type: Text Classification
|
| 14 |
+
|
| 15 |
+
## Validation Metrics
|
| 16 |
+
loss: 1.4641646146774292
|
| 17 |
+
|
| 18 |
+
f1_macro: 0.11844416562107904
|
| 19 |
+
|
| 20 |
+
f1_micro: 0.4206773618538324
|
| 21 |
+
|
| 22 |
+
f1_weighted: 0.24913389560226964
|
| 23 |
+
|
| 24 |
+
precision_macro: 0.08413547237076649
|
| 25 |
+
|
| 26 |
+
precision_micro: 0.4206773618538324
|
| 27 |
+
|
| 28 |
+
precision_weighted: 0.17696944277630028
|
| 29 |
+
|
| 30 |
+
recall_macro: 0.2
|
| 31 |
+
|
| 32 |
+
recall_micro: 0.4206773618538324
|
| 33 |
+
|
| 34 |
+
recall_weighted: 0.4206773618538324
|
| 35 |
+
|
| 36 |
+
accuracy: 0.4206773618538324
|
checkpoint-705/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 5,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "Misdirection",
|
| 15 |
+
"1": "Not Dark Pattern",
|
| 16 |
+
"2": "Scarcity",
|
| 17 |
+
"3": "Social Proof",
|
| 18 |
+
"4": "Urgency"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"Misdirection": 0,
|
| 24 |
+
"Not Dark Pattern": 1,
|
| 25 |
+
"Scarcity": 2,
|
| 26 |
+
"Social Proof": 3,
|
| 27 |
+
"Urgency": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "bert",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.48.0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 30522
|
| 42 |
+
}
|
checkpoint-705/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6084e05b8589034e90513778bb88bf6fa89bc2abfe946fa2b6425a7dd45bbee7
|
| 3 |
+
size 437967876
|
checkpoint-705/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b999e16b7db5be3eca5e4b4471018aead10b907c79d19e1408635611f9eb211
|
| 3 |
+
size 876051194
|
checkpoint-705/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dcaafb194f5701716fa357bed51d82227db84b369f87a3c3c726bbd753420a9
|
| 3 |
+
size 13990
|
checkpoint-705/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afbad54678cf40534f1db52f6ae133f359379409d6a6d1774fe14f02ff289a31
|
| 3 |
+
size 1064
|
checkpoint-705/trainer_state.json
ADDED
|
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.4641646146774292,
|
| 3 |
+
"best_model_checkpoint": "BertDPFinal/checkpoint-705",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 705,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04964539007092199,
|
| 13 |
+
"grad_norm": 6.189653396606445,
|
| 14 |
+
"learning_rate": 4.929577464788732e-05,
|
| 15 |
+
"loss": 1.5168,
|
| 16 |
+
"step": 7
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09929078014184398,
|
| 20 |
+
"grad_norm": 7.9828901290893555,
|
| 21 |
+
"learning_rate": 9.859154929577464e-05,
|
| 22 |
+
"loss": 1.2736,
|
| 23 |
+
"step": 14
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14893617021276595,
|
| 27 |
+
"grad_norm": 12.816457748413086,
|
| 28 |
+
"learning_rate": 0.00014788732394366196,
|
| 29 |
+
"loss": 1.024,
|
| 30 |
+
"step": 21
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.19858156028368795,
|
| 34 |
+
"grad_norm": 8.497725486755371,
|
| 35 |
+
"learning_rate": 0.00019718309859154928,
|
| 36 |
+
"loss": 0.8878,
|
| 37 |
+
"step": 28
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24822695035460993,
|
| 41 |
+
"grad_norm": 7.167214870452881,
|
| 42 |
+
"learning_rate": 0.0002464788732394366,
|
| 43 |
+
"loss": 0.5711,
|
| 44 |
+
"step": 35
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2978723404255319,
|
| 48 |
+
"grad_norm": 7.1105241775512695,
|
| 49 |
+
"learning_rate": 0.0002957746478873239,
|
| 50 |
+
"loss": 0.4673,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3475177304964539,
|
| 55 |
+
"grad_norm": 5.829805850982666,
|
| 56 |
+
"learning_rate": 0.00034507042253521125,
|
| 57 |
+
"loss": 0.5239,
|
| 58 |
+
"step": 49
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3971631205673759,
|
| 62 |
+
"grad_norm": 1.8413548469543457,
|
| 63 |
+
"learning_rate": 0.00039436619718309857,
|
| 64 |
+
"loss": 0.6027,
|
| 65 |
+
"step": 56
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.44680851063829785,
|
| 69 |
+
"grad_norm": 18.90794563293457,
|
| 70 |
+
"learning_rate": 0.00044366197183098594,
|
| 71 |
+
"loss": 0.5557,
|
| 72 |
+
"step": 63
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.49645390070921985,
|
| 76 |
+
"grad_norm": 7.452854633331299,
|
| 77 |
+
"learning_rate": 0.0004929577464788732,
|
| 78 |
+
"loss": 1.0656,
|
| 79 |
+
"step": 70
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5460992907801419,
|
| 83 |
+
"grad_norm": 9.592812538146973,
|
| 84 |
+
"learning_rate": 0.0004952681388012618,
|
| 85 |
+
"loss": 0.5374,
|
| 86 |
+
"step": 77
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5957446808510638,
|
| 90 |
+
"grad_norm": 39.28833770751953,
|
| 91 |
+
"learning_rate": 0.0004897476340694006,
|
| 92 |
+
"loss": 1.3247,
|
| 93 |
+
"step": 84
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6453900709219859,
|
| 97 |
+
"grad_norm": 7.832529067993164,
|
| 98 |
+
"learning_rate": 0.00048422712933753943,
|
| 99 |
+
"loss": 0.9205,
|
| 100 |
+
"step": 91
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6950354609929078,
|
| 104 |
+
"grad_norm": 9.48823356628418,
|
| 105 |
+
"learning_rate": 0.0004787066246056783,
|
| 106 |
+
"loss": 0.6197,
|
| 107 |
+
"step": 98
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7446808510638298,
|
| 111 |
+
"grad_norm": 4.825063228607178,
|
| 112 |
+
"learning_rate": 0.00047318611987381704,
|
| 113 |
+
"loss": 0.8266,
|
| 114 |
+
"step": 105
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7943262411347518,
|
| 118 |
+
"grad_norm": 20.6807804107666,
|
| 119 |
+
"learning_rate": 0.00046766561514195585,
|
| 120 |
+
"loss": 0.7012,
|
| 121 |
+
"step": 112
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8439716312056738,
|
| 125 |
+
"grad_norm": 17.61189079284668,
|
| 126 |
+
"learning_rate": 0.00046214511041009466,
|
| 127 |
+
"loss": 0.8756,
|
| 128 |
+
"step": 119
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8936170212765957,
|
| 132 |
+
"grad_norm": 17.65863609313965,
|
| 133 |
+
"learning_rate": 0.00045662460567823346,
|
| 134 |
+
"loss": 0.8106,
|
| 135 |
+
"step": 126
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9432624113475178,
|
| 139 |
+
"grad_norm": 8.734783172607422,
|
| 140 |
+
"learning_rate": 0.00045110410094637227,
|
| 141 |
+
"loss": 0.8036,
|
| 142 |
+
"step": 133
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9929078014184397,
|
| 146 |
+
"grad_norm": 10.476834297180176,
|
| 147 |
+
"learning_rate": 0.0004455835962145111,
|
| 148 |
+
"loss": 1.7022,
|
| 149 |
+
"step": 140
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.4206773618538324,
|
| 154 |
+
"eval_f1_macro": 0.11844416562107904,
|
| 155 |
+
"eval_f1_micro": 0.4206773618538324,
|
| 156 |
+
"eval_f1_weighted": 0.24913389560226964,
|
| 157 |
+
"eval_loss": 1.7349635362625122,
|
| 158 |
+
"eval_precision_macro": 0.08413547237076649,
|
| 159 |
+
"eval_precision_micro": 0.4206773618538324,
|
| 160 |
+
"eval_precision_weighted": 0.17696944277630028,
|
| 161 |
+
"eval_recall_macro": 0.2,
|
| 162 |
+
"eval_recall_micro": 0.4206773618538324,
|
| 163 |
+
"eval_recall_weighted": 0.4206773618538324,
|
| 164 |
+
"eval_runtime": 93.8033,
|
| 165 |
+
"eval_samples_per_second": 5.981,
|
| 166 |
+
"eval_steps_per_second": 0.192,
|
| 167 |
+
"step": 141
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.0425531914893618,
|
| 171 |
+
"grad_norm": 4.221170425415039,
|
| 172 |
+
"learning_rate": 0.00044006309148264983,
|
| 173 |
+
"loss": 1.7519,
|
| 174 |
+
"step": 147
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.0921985815602837,
|
| 178 |
+
"grad_norm": 9.088502883911133,
|
| 179 |
+
"learning_rate": 0.0004345425867507887,
|
| 180 |
+
"loss": 1.6266,
|
| 181 |
+
"step": 154
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.1418439716312057,
|
| 185 |
+
"grad_norm": 4.848515510559082,
|
| 186 |
+
"learning_rate": 0.00042902208201892744,
|
| 187 |
+
"loss": 1.4517,
|
| 188 |
+
"step": 161
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.1914893617021276,
|
| 192 |
+
"grad_norm": 5.071916580200195,
|
| 193 |
+
"learning_rate": 0.00042350157728706625,
|
| 194 |
+
"loss": 1.6065,
|
| 195 |
+
"step": 168
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.2411347517730495,
|
| 199 |
+
"grad_norm": 5.36010217666626,
|
| 200 |
+
"learning_rate": 0.00041798107255520506,
|
| 201 |
+
"loss": 1.5091,
|
| 202 |
+
"step": 175
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.2907801418439715,
|
| 206 |
+
"grad_norm": 7.226471900939941,
|
| 207 |
+
"learning_rate": 0.00041246056782334386,
|
| 208 |
+
"loss": 1.4226,
|
| 209 |
+
"step": 182
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.3404255319148937,
|
| 213 |
+
"grad_norm": 8.1095609664917,
|
| 214 |
+
"learning_rate": 0.00040694006309148267,
|
| 215 |
+
"loss": 1.5773,
|
| 216 |
+
"step": 189
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.3900709219858156,
|
| 220 |
+
"grad_norm": 7.920806407928467,
|
| 221 |
+
"learning_rate": 0.0004014195583596215,
|
| 222 |
+
"loss": 1.5676,
|
| 223 |
+
"step": 196
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.4397163120567376,
|
| 227 |
+
"grad_norm": 5.325973033905029,
|
| 228 |
+
"learning_rate": 0.00039589905362776023,
|
| 229 |
+
"loss": 1.5114,
|
| 230 |
+
"step": 203
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.4893617021276595,
|
| 234 |
+
"grad_norm": 2.933687448501587,
|
| 235 |
+
"learning_rate": 0.0003903785488958991,
|
| 236 |
+
"loss": 1.5683,
|
| 237 |
+
"step": 210
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.5390070921985815,
|
| 241 |
+
"grad_norm": 6.924223899841309,
|
| 242 |
+
"learning_rate": 0.00038485804416403784,
|
| 243 |
+
"loss": 1.4303,
|
| 244 |
+
"step": 217
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.5886524822695036,
|
| 248 |
+
"grad_norm": 7.421421051025391,
|
| 249 |
+
"learning_rate": 0.00037933753943217665,
|
| 250 |
+
"loss": 1.5537,
|
| 251 |
+
"step": 224
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.6382978723404256,
|
| 255 |
+
"grad_norm": 13.512285232543945,
|
| 256 |
+
"learning_rate": 0.00037381703470031546,
|
| 257 |
+
"loss": 1.5651,
|
| 258 |
+
"step": 231
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.6879432624113475,
|
| 262 |
+
"grad_norm": 4.299217224121094,
|
| 263 |
+
"learning_rate": 0.00036829652996845427,
|
| 264 |
+
"loss": 1.454,
|
| 265 |
+
"step": 238
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.7375886524822695,
|
| 269 |
+
"grad_norm": 6.256487846374512,
|
| 270 |
+
"learning_rate": 0.00036277602523659307,
|
| 271 |
+
"loss": 1.391,
|
| 272 |
+
"step": 245
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.7872340425531914,
|
| 276 |
+
"grad_norm": 7.585392951965332,
|
| 277 |
+
"learning_rate": 0.0003572555205047319,
|
| 278 |
+
"loss": 1.5158,
|
| 279 |
+
"step": 252
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.8368794326241136,
|
| 283 |
+
"grad_norm": 5.252770900726318,
|
| 284 |
+
"learning_rate": 0.00035173501577287063,
|
| 285 |
+
"loss": 1.4638,
|
| 286 |
+
"step": 259
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.8865248226950353,
|
| 290 |
+
"grad_norm": 9.459006309509277,
|
| 291 |
+
"learning_rate": 0.0003462145110410095,
|
| 292 |
+
"loss": 1.5131,
|
| 293 |
+
"step": 266
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.9361702127659575,
|
| 297 |
+
"grad_norm": 8.648561477661133,
|
| 298 |
+
"learning_rate": 0.00034069400630914825,
|
| 299 |
+
"loss": 1.5579,
|
| 300 |
+
"step": 273
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.9858156028368794,
|
| 304 |
+
"grad_norm": 6.65281867980957,
|
| 305 |
+
"learning_rate": 0.0003351735015772871,
|
| 306 |
+
"loss": 1.5215,
|
| 307 |
+
"step": 280
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.0,
|
| 311 |
+
"eval_accuracy": 0.4206773618538324,
|
| 312 |
+
"eval_f1_macro": 0.11844416562107904,
|
| 313 |
+
"eval_f1_micro": 0.4206773618538324,
|
| 314 |
+
"eval_f1_weighted": 0.24913389560226964,
|
| 315 |
+
"eval_loss": 1.4817699193954468,
|
| 316 |
+
"eval_precision_macro": 0.08413547237076649,
|
| 317 |
+
"eval_precision_micro": 0.4206773618538324,
|
| 318 |
+
"eval_precision_weighted": 0.17696944277630028,
|
| 319 |
+
"eval_recall_macro": 0.2,
|
| 320 |
+
"eval_recall_micro": 0.4206773618538324,
|
| 321 |
+
"eval_recall_weighted": 0.4206773618538324,
|
| 322 |
+
"eval_runtime": 101.5312,
|
| 323 |
+
"eval_samples_per_second": 5.525,
|
| 324 |
+
"eval_steps_per_second": 0.177,
|
| 325 |
+
"step": 282
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.0354609929078014,
|
| 329 |
+
"grad_norm": 11.359745979309082,
|
| 330 |
+
"learning_rate": 0.00032965299684542586,
|
| 331 |
+
"loss": 1.4603,
|
| 332 |
+
"step": 287
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.0851063829787235,
|
| 336 |
+
"grad_norm": 3.0409834384918213,
|
| 337 |
+
"learning_rate": 0.00032413249211356467,
|
| 338 |
+
"loss": 1.5188,
|
| 339 |
+
"step": 294
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.1347517730496453,
|
| 343 |
+
"grad_norm": 8.440783500671387,
|
| 344 |
+
"learning_rate": 0.0003186119873817035,
|
| 345 |
+
"loss": 1.543,
|
| 346 |
+
"step": 301
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.1843971631205674,
|
| 350 |
+
"grad_norm": 4.947517395019531,
|
| 351 |
+
"learning_rate": 0.0003130914826498423,
|
| 352 |
+
"loss": 1.5058,
|
| 353 |
+
"step": 308
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.2340425531914896,
|
| 357 |
+
"grad_norm": 11.440240859985352,
|
| 358 |
+
"learning_rate": 0.00030757097791798103,
|
| 359 |
+
"loss": 1.5307,
|
| 360 |
+
"step": 315
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.2836879432624113,
|
| 364 |
+
"grad_norm": 5.052453994750977,
|
| 365 |
+
"learning_rate": 0.0003020504731861199,
|
| 366 |
+
"loss": 1.4709,
|
| 367 |
+
"step": 322
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.3333333333333335,
|
| 371 |
+
"grad_norm": 5.959723472595215,
|
| 372 |
+
"learning_rate": 0.00029652996845425865,
|
| 373 |
+
"loss": 1.5479,
|
| 374 |
+
"step": 329
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.382978723404255,
|
| 378 |
+
"grad_norm": 11.568524360656738,
|
| 379 |
+
"learning_rate": 0.0002910094637223975,
|
| 380 |
+
"loss": 1.4821,
|
| 381 |
+
"step": 336
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.4326241134751774,
|
| 385 |
+
"grad_norm": 5.613851070404053,
|
| 386 |
+
"learning_rate": 0.00028548895899053626,
|
| 387 |
+
"loss": 1.4432,
|
| 388 |
+
"step": 343
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.482269503546099,
|
| 392 |
+
"grad_norm": 5.919626235961914,
|
| 393 |
+
"learning_rate": 0.00027996845425867507,
|
| 394 |
+
"loss": 1.4674,
|
| 395 |
+
"step": 350
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.5319148936170213,
|
| 399 |
+
"grad_norm": 4.506762981414795,
|
| 400 |
+
"learning_rate": 0.0002744479495268139,
|
| 401 |
+
"loss": 1.5441,
|
| 402 |
+
"step": 357
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.581560283687943,
|
| 406 |
+
"grad_norm": 5.5926513671875,
|
| 407 |
+
"learning_rate": 0.0002689274447949527,
|
| 408 |
+
"loss": 1.4295,
|
| 409 |
+
"step": 364
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.631205673758865,
|
| 413 |
+
"grad_norm": 4.040436744689941,
|
| 414 |
+
"learning_rate": 0.0002634069400630915,
|
| 415 |
+
"loss": 1.4721,
|
| 416 |
+
"step": 371
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.6808510638297873,
|
| 420 |
+
"grad_norm": 7.786831378936768,
|
| 421 |
+
"learning_rate": 0.0002578864353312303,
|
| 422 |
+
"loss": 1.4557,
|
| 423 |
+
"step": 378
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.7304964539007095,
|
| 427 |
+
"grad_norm": 8.222126960754395,
|
| 428 |
+
"learning_rate": 0.00025236593059936905,
|
| 429 |
+
"loss": 1.5841,
|
| 430 |
+
"step": 385
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.780141843971631,
|
| 434 |
+
"grad_norm": 8.391121864318848,
|
| 435 |
+
"learning_rate": 0.0002468454258675079,
|
| 436 |
+
"loss": 1.5307,
|
| 437 |
+
"step": 392
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.829787234042553,
|
| 441 |
+
"grad_norm": 8.323009490966797,
|
| 442 |
+
"learning_rate": 0.0002413249211356467,
|
| 443 |
+
"loss": 1.6008,
|
| 444 |
+
"step": 399
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.879432624113475,
|
| 448 |
+
"grad_norm": 3.1226701736450195,
|
| 449 |
+
"learning_rate": 0.0002358044164037855,
|
| 450 |
+
"loss": 1.5368,
|
| 451 |
+
"step": 406
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.9290780141843973,
|
| 455 |
+
"grad_norm": 7.813109397888184,
|
| 456 |
+
"learning_rate": 0.0002302839116719243,
|
| 457 |
+
"loss": 1.5191,
|
| 458 |
+
"step": 413
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.978723404255319,
|
| 462 |
+
"grad_norm": 7.449869632720947,
|
| 463 |
+
"learning_rate": 0.00022476340694006308,
|
| 464 |
+
"loss": 1.4775,
|
| 465 |
+
"step": 420
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.0,
|
| 469 |
+
"eval_accuracy": 0.4206773618538324,
|
| 470 |
+
"eval_f1_macro": 0.11844416562107904,
|
| 471 |
+
"eval_f1_micro": 0.4206773618538324,
|
| 472 |
+
"eval_f1_weighted": 0.24913389560226964,
|
| 473 |
+
"eval_loss": 1.4698808193206787,
|
| 474 |
+
"eval_precision_macro": 0.08413547237076649,
|
| 475 |
+
"eval_precision_micro": 0.4206773618538324,
|
| 476 |
+
"eval_precision_weighted": 0.17696944277630028,
|
| 477 |
+
"eval_recall_macro": 0.2,
|
| 478 |
+
"eval_recall_micro": 0.4206773618538324,
|
| 479 |
+
"eval_recall_weighted": 0.4206773618538324,
|
| 480 |
+
"eval_runtime": 95.8155,
|
| 481 |
+
"eval_samples_per_second": 5.855,
|
| 482 |
+
"eval_steps_per_second": 0.188,
|
| 483 |
+
"step": 423
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.028368794326241,
|
| 487 |
+
"grad_norm": 3.7486603260040283,
|
| 488 |
+
"learning_rate": 0.0002192429022082019,
|
| 489 |
+
"loss": 1.4908,
|
| 490 |
+
"step": 427
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.078014184397163,
|
| 494 |
+
"grad_norm": 7.605023384094238,
|
| 495 |
+
"learning_rate": 0.0002137223974763407,
|
| 496 |
+
"loss": 1.4668,
|
| 497 |
+
"step": 434
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.127659574468085,
|
| 501 |
+
"grad_norm": 8.043049812316895,
|
| 502 |
+
"learning_rate": 0.0002082018927444795,
|
| 503 |
+
"loss": 1.4578,
|
| 504 |
+
"step": 441
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.1773049645390072,
|
| 508 |
+
"grad_norm": 9.950433731079102,
|
| 509 |
+
"learning_rate": 0.00020268138801261828,
|
| 510 |
+
"loss": 1.5122,
|
| 511 |
+
"step": 448
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.226950354609929,
|
| 515 |
+
"grad_norm": 9.23243522644043,
|
| 516 |
+
"learning_rate": 0.0001971608832807571,
|
| 517 |
+
"loss": 1.4766,
|
| 518 |
+
"step": 455
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.276595744680851,
|
| 522 |
+
"grad_norm": 7.5233283042907715,
|
| 523 |
+
"learning_rate": 0.0001916403785488959,
|
| 524 |
+
"loss": 1.5762,
|
| 525 |
+
"step": 462
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.326241134751773,
|
| 529 |
+
"grad_norm": 5.127943515777588,
|
| 530 |
+
"learning_rate": 0.0001861198738170347,
|
| 531 |
+
"loss": 1.5169,
|
| 532 |
+
"step": 469
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.375886524822695,
|
| 536 |
+
"grad_norm": 7.124870777130127,
|
| 537 |
+
"learning_rate": 0.00018059936908517349,
|
| 538 |
+
"loss": 1.431,
|
| 539 |
+
"step": 476
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.425531914893617,
|
| 543 |
+
"grad_norm": 5.022177696228027,
|
| 544 |
+
"learning_rate": 0.0001750788643533123,
|
| 545 |
+
"loss": 1.5414,
|
| 546 |
+
"step": 483
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.475177304964539,
|
| 550 |
+
"grad_norm": 6.953367710113525,
|
| 551 |
+
"learning_rate": 0.0001695583596214511,
|
| 552 |
+
"loss": 1.4909,
|
| 553 |
+
"step": 490
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.524822695035461,
|
| 557 |
+
"grad_norm": 7.820435047149658,
|
| 558 |
+
"learning_rate": 0.0001640378548895899,
|
| 559 |
+
"loss": 1.5528,
|
| 560 |
+
"step": 497
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.574468085106383,
|
| 564 |
+
"grad_norm": 4.93435525894165,
|
| 565 |
+
"learning_rate": 0.0001585173501577287,
|
| 566 |
+
"loss": 1.5442,
|
| 567 |
+
"step": 504
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.624113475177305,
|
| 571 |
+
"grad_norm": 5.903745651245117,
|
| 572 |
+
"learning_rate": 0.0001529968454258675,
|
| 573 |
+
"loss": 1.4897,
|
| 574 |
+
"step": 511
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 3.673758865248227,
|
| 578 |
+
"grad_norm": 4.987692832946777,
|
| 579 |
+
"learning_rate": 0.0001474763406940063,
|
| 580 |
+
"loss": 1.5229,
|
| 581 |
+
"step": 518
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 3.723404255319149,
|
| 585 |
+
"grad_norm": 7.9324493408203125,
|
| 586 |
+
"learning_rate": 0.0001419558359621451,
|
| 587 |
+
"loss": 1.5382,
|
| 588 |
+
"step": 525
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 3.773049645390071,
|
| 592 |
+
"grad_norm": 4.636258602142334,
|
| 593 |
+
"learning_rate": 0.00013643533123028391,
|
| 594 |
+
"loss": 1.4008,
|
| 595 |
+
"step": 532
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 3.8226950354609928,
|
| 599 |
+
"grad_norm": 7.370692253112793,
|
| 600 |
+
"learning_rate": 0.0001309148264984227,
|
| 601 |
+
"loss": 1.4394,
|
| 602 |
+
"step": 539
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.872340425531915,
|
| 606 |
+
"grad_norm": 5.526173114776611,
|
| 607 |
+
"learning_rate": 0.0001253943217665615,
|
| 608 |
+
"loss": 1.494,
|
| 609 |
+
"step": 546
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.921985815602837,
|
| 613 |
+
"grad_norm": 5.848151206970215,
|
| 614 |
+
"learning_rate": 0.00011987381703470032,
|
| 615 |
+
"loss": 1.4898,
|
| 616 |
+
"step": 553
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 3.971631205673759,
|
| 620 |
+
"grad_norm": 8.235275268554688,
|
| 621 |
+
"learning_rate": 0.00011435331230283911,
|
| 622 |
+
"loss": 1.4544,
|
| 623 |
+
"step": 560
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 4.0,
|
| 627 |
+
"eval_accuracy": 0.4206773618538324,
|
| 628 |
+
"eval_f1_macro": 0.11844416562107904,
|
| 629 |
+
"eval_f1_micro": 0.4206773618538324,
|
| 630 |
+
"eval_f1_weighted": 0.24913389560226964,
|
| 631 |
+
"eval_loss": 1.4689174890518188,
|
| 632 |
+
"eval_precision_macro": 0.08413547237076649,
|
| 633 |
+
"eval_precision_micro": 0.4206773618538324,
|
| 634 |
+
"eval_precision_weighted": 0.17696944277630028,
|
| 635 |
+
"eval_recall_macro": 0.2,
|
| 636 |
+
"eval_recall_micro": 0.4206773618538324,
|
| 637 |
+
"eval_recall_weighted": 0.4206773618538324,
|
| 638 |
+
"eval_runtime": 104.2168,
|
| 639 |
+
"eval_samples_per_second": 5.383,
|
| 640 |
+
"eval_steps_per_second": 0.173,
|
| 641 |
+
"step": 564
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 4.0212765957446805,
|
| 645 |
+
"grad_norm": 5.463527202606201,
|
| 646 |
+
"learning_rate": 0.00010883280757097792,
|
| 647 |
+
"loss": 1.4317,
|
| 648 |
+
"step": 567
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 4.070921985815603,
|
| 652 |
+
"grad_norm": 10.034351348876953,
|
| 653 |
+
"learning_rate": 0.00010331230283911672,
|
| 654 |
+
"loss": 1.4152,
|
| 655 |
+
"step": 574
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 4.120567375886525,
|
| 659 |
+
"grad_norm": 4.740342140197754,
|
| 660 |
+
"learning_rate": 9.779179810725552e-05,
|
| 661 |
+
"loss": 1.4476,
|
| 662 |
+
"step": 581
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 4.170212765957447,
|
| 666 |
+
"grad_norm": 6.606863498687744,
|
| 667 |
+
"learning_rate": 9.227129337539432e-05,
|
| 668 |
+
"loss": 1.4909,
|
| 669 |
+
"step": 588
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 4.219858156028369,
|
| 673 |
+
"grad_norm": 6.777315616607666,
|
| 674 |
+
"learning_rate": 8.675078864353312e-05,
|
| 675 |
+
"loss": 1.5223,
|
| 676 |
+
"step": 595
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 4.2695035460992905,
|
| 680 |
+
"grad_norm": 5.83721399307251,
|
| 681 |
+
"learning_rate": 8.123028391167192e-05,
|
| 682 |
+
"loss": 1.4517,
|
| 683 |
+
"step": 602
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 4.319148936170213,
|
| 687 |
+
"grad_norm": 3.974072217941284,
|
| 688 |
+
"learning_rate": 7.570977917981072e-05,
|
| 689 |
+
"loss": 1.4083,
|
| 690 |
+
"step": 609
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 4.368794326241135,
|
| 694 |
+
"grad_norm": 7.428138256072998,
|
| 695 |
+
"learning_rate": 7.018927444794952e-05,
|
| 696 |
+
"loss": 1.496,
|
| 697 |
+
"step": 616
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.418439716312057,
|
| 701 |
+
"grad_norm": 5.983969211578369,
|
| 702 |
+
"learning_rate": 6.466876971608832e-05,
|
| 703 |
+
"loss": 1.4731,
|
| 704 |
+
"step": 623
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.468085106382979,
|
| 708 |
+
"grad_norm": 9.003389358520508,
|
| 709 |
+
"learning_rate": 5.914826498422713e-05,
|
| 710 |
+
"loss": 1.4909,
|
| 711 |
+
"step": 630
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.5177304964539005,
|
| 715 |
+
"grad_norm": 8.925243377685547,
|
| 716 |
+
"learning_rate": 5.362776025236593e-05,
|
| 717 |
+
"loss": 1.5555,
|
| 718 |
+
"step": 637
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.567375886524823,
|
| 722 |
+
"grad_norm": 4.844193458557129,
|
| 723 |
+
"learning_rate": 4.810725552050473e-05,
|
| 724 |
+
"loss": 1.4563,
|
| 725 |
+
"step": 644
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.617021276595745,
|
| 729 |
+
"grad_norm": 3.9511518478393555,
|
| 730 |
+
"learning_rate": 4.258675078864353e-05,
|
| 731 |
+
"loss": 1.5393,
|
| 732 |
+
"step": 651
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 4.666666666666667,
|
| 736 |
+
"grad_norm": 7.398727893829346,
|
| 737 |
+
"learning_rate": 3.706624605678233e-05,
|
| 738 |
+
"loss": 1.6317,
|
| 739 |
+
"step": 658
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 4.716312056737589,
|
| 743 |
+
"grad_norm": 5.623064041137695,
|
| 744 |
+
"learning_rate": 3.154574132492113e-05,
|
| 745 |
+
"loss": 1.4246,
|
| 746 |
+
"step": 665
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 4.76595744680851,
|
| 750 |
+
"grad_norm": 9.576728820800781,
|
| 751 |
+
"learning_rate": 2.6025236593059938e-05,
|
| 752 |
+
"loss": 1.4539,
|
| 753 |
+
"step": 672
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.815602836879433,
|
| 757 |
+
"grad_norm": 4.443638801574707,
|
| 758 |
+
"learning_rate": 2.0504731861198738e-05,
|
| 759 |
+
"loss": 1.524,
|
| 760 |
+
"step": 679
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.865248226950355,
|
| 764 |
+
"grad_norm": 7.209597587585449,
|
| 765 |
+
"learning_rate": 1.498422712933754e-05,
|
| 766 |
+
"loss": 1.4586,
|
| 767 |
+
"step": 686
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 4.914893617021277,
|
| 771 |
+
"grad_norm": 3.1652464866638184,
|
| 772 |
+
"learning_rate": 9.46372239747634e-06,
|
| 773 |
+
"loss": 1.5418,
|
| 774 |
+
"step": 693
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 4.964539007092198,
|
| 778 |
+
"grad_norm": 6.17334508895874,
|
| 779 |
+
"learning_rate": 3.943217665615141e-06,
|
| 780 |
+
"loss": 1.4319,
|
| 781 |
+
"step": 700
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 5.0,
|
| 785 |
+
"eval_accuracy": 0.4206773618538324,
|
| 786 |
+
"eval_f1_macro": 0.11844416562107904,
|
| 787 |
+
"eval_f1_micro": 0.4206773618538324,
|
| 788 |
+
"eval_f1_weighted": 0.24913389560226964,
|
| 789 |
+
"eval_loss": 1.4641646146774292,
|
| 790 |
+
"eval_precision_macro": 0.08413547237076649,
|
| 791 |
+
"eval_precision_micro": 0.4206773618538324,
|
| 792 |
+
"eval_precision_weighted": 0.17696944277630028,
|
| 793 |
+
"eval_recall_macro": 0.2,
|
| 794 |
+
"eval_recall_micro": 0.4206773618538324,
|
| 795 |
+
"eval_recall_weighted": 0.4206773618538324,
|
| 796 |
+
"eval_runtime": 111.7138,
|
| 797 |
+
"eval_samples_per_second": 5.022,
|
| 798 |
+
"eval_steps_per_second": 0.161,
|
| 799 |
+
"step": 705
|
| 800 |
+
}
|
| 801 |
+
],
|
| 802 |
+
"logging_steps": 7,
|
| 803 |
+
"max_steps": 705,
|
| 804 |
+
"num_input_tokens_seen": 0,
|
| 805 |
+
"num_train_epochs": 5,
|
| 806 |
+
"save_steps": 500,
|
| 807 |
+
"stateful_callbacks": {
|
| 808 |
+
"EarlyStoppingCallback": {
|
| 809 |
+
"args": {
|
| 810 |
+
"early_stopping_patience": 5,
|
| 811 |
+
"early_stopping_threshold": 0.01
|
| 812 |
+
},
|
| 813 |
+
"attributes": {
|
| 814 |
+
"early_stopping_patience_counter": 2
|
| 815 |
+
}
|
| 816 |
+
},
|
| 817 |
+
"TrainerControl": {
|
| 818 |
+
"args": {
|
| 819 |
+
"should_epoch_stop": false,
|
| 820 |
+
"should_evaluate": false,
|
| 821 |
+
"should_log": false,
|
| 822 |
+
"should_save": true,
|
| 823 |
+
"should_training_stop": true
|
| 824 |
+
},
|
| 825 |
+
"attributes": {}
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"total_flos": 738046389611520.0,
|
| 829 |
+
"train_batch_size": 16,
|
| 830 |
+
"trial_name": null,
|
| 831 |
+
"trial_params": null
|
| 832 |
+
}
|
checkpoint-705/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f702ce33bd650b54b73eb9545354b7e46b94818b014b98c53a37a9e5e1f8af2b
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 5,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "Misdirection",
|
| 15 |
+
"1": "Not Dark Pattern",
|
| 16 |
+
"2": "Scarcity",
|
| 17 |
+
"3": "Social Proof",
|
| 18 |
+
"4": "Urgency"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"Misdirection": 0,
|
| 24 |
+
"Not Dark Pattern": 1,
|
| 25 |
+
"Scarcity": 2,
|
| 26 |
+
"Social Proof": 3,
|
| 27 |
+
"Urgency": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "bert",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.48.0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 30522
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6084e05b8589034e90513778bb88bf6fa89bc2abfe946fa2b6425a7dd45bbee7
|
| 3 |
+
size 437967876
|
runs/Jan19_13-42-52_r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3/events.out.tfevents.1737294174.r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3.158.0
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 sha256:8e5c7dfc2bd3164f69b922e2219dd1295dfa138c725f83e0c33167fe1c0458bc
|
| 3 |
+
size 30901
|
runs/Jan19_13-42-52_r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3/events.out.tfevents.1737301796.r-necromancer7-darkpatterns-loa9innb-2a832-ddxk3.158.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5871d51fc1bca3593284149590c413e7454487056f37dc1153ee6ed991a2cbc7
|
| 3 |
+
size 921
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f702ce33bd650b54b73eb9545354b7e46b94818b014b98c53a37a9e5e1f8af2b
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "BertDPFinal/autotrain-data",
|
| 3 |
+
"model": "google-bert/bert-base-uncased",
|
| 4 |
+
"lr": 0.0005,
|
| 5 |
+
"epochs": 5,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 16,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "linear",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"text_column": "autotrain_text",
|
| 18 |
+
"target_column": "autotrain_label",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "BertDPFinal",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"eval_strategy": "epoch",
|
| 26 |
+
"username": "necromancer7",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|