Upload folder using huggingface_hub
Browse files- README.md +38 -0
- checkpoint-1000/config.json +44 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +1276 -0
- checkpoint-1000/training_args.bin +3 -0
- config.json +44 -0
- model.safetensors +3 -0
- runs/Jan13_14-38-13_r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1/events.out.tfevents.1736779095.r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1.71.0 +2 -2
- runs/Jan13_14-38-13_r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1/events.out.tfevents.1736779539.r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1.71.1 +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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
datasets:
|
| 10 |
+
- dair-ai/emotion
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Trained Using AutoTrain
|
| 14 |
+
|
| 15 |
+
- Problem type: Text Classification
|
| 16 |
+
|
| 17 |
+
## Validation Metrics
|
| 18 |
+
loss: 0.13341853022575378
|
| 19 |
+
|
| 20 |
+
f1_macro: 0.9169826832623412
|
| 21 |
+
|
| 22 |
+
f1_micro: 0.943
|
| 23 |
+
|
| 24 |
+
f1_weighted: 0.9427985114313238
|
| 25 |
+
|
| 26 |
+
precision_macro: 0.9227534317185495
|
| 27 |
+
|
| 28 |
+
precision_micro: 0.943
|
| 29 |
+
|
| 30 |
+
precision_weighted: 0.9430912986498113
|
| 31 |
+
|
| 32 |
+
recall_macro: 0.9119580961776227
|
| 33 |
+
|
| 34 |
+
recall_micro: 0.943
|
| 35 |
+
|
| 36 |
+
recall_weighted: 0.943
|
| 37 |
+
|
| 38 |
+
accuracy: 0.943
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 6,
|
| 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": "sadness",
|
| 15 |
+
"1": "joy",
|
| 16 |
+
"2": "love",
|
| 17 |
+
"3": "anger",
|
| 18 |
+
"4": "fear",
|
| 19 |
+
"5": "surprise"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"anger": 3,
|
| 25 |
+
"fear": 4,
|
| 26 |
+
"joy": 1,
|
| 27 |
+
"love": 2,
|
| 28 |
+
"sadness": 0,
|
| 29 |
+
"surprise": 5
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "bert",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.47.1",
|
| 41 |
+
"type_vocab_size": 2,
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 30522
|
| 44 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c23242b997142673a26c3d533fe71e0f8559f2ec9d26881534cf0619171bff5e
|
| 3 |
+
size 437970952
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a07cbbc87d7d16506faefb64d3714c2d8350878754ed4708271a432d3f11ce8c
|
| 3 |
+
size 876062970
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c31f8a77bd3c3bc108230506868623a28d60db2df0f687aa62b4e0ff3e613ce8
|
| 3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ef71cc657dcc739b95a9a1feb99f0f00b769d40f0c85458c7a0c4875c92051
|
| 3 |
+
size 1064
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,1276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.13341853022575378,
|
| 3 |
+
"best_model_checkpoint": "Emotion-Classification/checkpoint-1000",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.024,
|
| 13 |
+
"grad_norm": 4.761784076690674,
|
| 14 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 15 |
+
"loss": 1.8584,
|
| 16 |
+
"step": 6
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.048,
|
| 20 |
+
"grad_norm": 5.941750526428223,
|
| 21 |
+
"learning_rate": 4.800000000000001e-06,
|
| 22 |
+
"loss": 1.8129,
|
| 23 |
+
"step": 12
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.072,
|
| 27 |
+
"grad_norm": 5.263009071350098,
|
| 28 |
+
"learning_rate": 7.2e-06,
|
| 29 |
+
"loss": 1.7576,
|
| 30 |
+
"step": 18
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.096,
|
| 34 |
+
"grad_norm": 3.814999580383301,
|
| 35 |
+
"learning_rate": 9.600000000000001e-06,
|
| 36 |
+
"loss": 1.6755,
|
| 37 |
+
"step": 24
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.12,
|
| 41 |
+
"grad_norm": 4.710057735443115,
|
| 42 |
+
"learning_rate": 1.2e-05,
|
| 43 |
+
"loss": 1.651,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.144,
|
| 48 |
+
"grad_norm": 4.196522235870361,
|
| 49 |
+
"learning_rate": 1.44e-05,
|
| 50 |
+
"loss": 1.6415,
|
| 51 |
+
"step": 36
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.168,
|
| 55 |
+
"grad_norm": 4.069035053253174,
|
| 56 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 57 |
+
"loss": 1.6045,
|
| 58 |
+
"step": 42
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.192,
|
| 62 |
+
"grad_norm": 2.729994535446167,
|
| 63 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 64 |
+
"loss": 1.5199,
|
| 65 |
+
"step": 48
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.216,
|
| 69 |
+
"grad_norm": 3.651451349258423,
|
| 70 |
+
"learning_rate": 2.16e-05,
|
| 71 |
+
"loss": 1.5483,
|
| 72 |
+
"step": 54
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.24,
|
| 76 |
+
"grad_norm": 3.8345696926116943,
|
| 77 |
+
"learning_rate": 2.4e-05,
|
| 78 |
+
"loss": 1.4484,
|
| 79 |
+
"step": 60
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.264,
|
| 83 |
+
"grad_norm": 5.036585807800293,
|
| 84 |
+
"learning_rate": 2.64e-05,
|
| 85 |
+
"loss": 1.352,
|
| 86 |
+
"step": 66
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.288,
|
| 90 |
+
"grad_norm": 4.797017574310303,
|
| 91 |
+
"learning_rate": 2.88e-05,
|
| 92 |
+
"loss": 1.2928,
|
| 93 |
+
"step": 72
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.312,
|
| 97 |
+
"grad_norm": 4.072025299072266,
|
| 98 |
+
"learning_rate": 3.12e-05,
|
| 99 |
+
"loss": 1.2858,
|
| 100 |
+
"step": 78
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.336,
|
| 104 |
+
"grad_norm": 4.3313727378845215,
|
| 105 |
+
"learning_rate": 3.3600000000000004e-05,
|
| 106 |
+
"loss": 1.1242,
|
| 107 |
+
"step": 84
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.36,
|
| 111 |
+
"grad_norm": 5.59000825881958,
|
| 112 |
+
"learning_rate": 3.56e-05,
|
| 113 |
+
"loss": 1.1086,
|
| 114 |
+
"step": 90
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.384,
|
| 118 |
+
"grad_norm": 8.562559127807617,
|
| 119 |
+
"learning_rate": 3.8e-05,
|
| 120 |
+
"loss": 0.9659,
|
| 121 |
+
"step": 96
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.408,
|
| 125 |
+
"grad_norm": 7.202652931213379,
|
| 126 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 127 |
+
"loss": 0.9103,
|
| 128 |
+
"step": 102
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.432,
|
| 132 |
+
"grad_norm": 6.920612812042236,
|
| 133 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 134 |
+
"loss": 0.8257,
|
| 135 |
+
"step": 108
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.456,
|
| 139 |
+
"grad_norm": 4.389594078063965,
|
| 140 |
+
"learning_rate": 4.52e-05,
|
| 141 |
+
"loss": 0.7882,
|
| 142 |
+
"step": 114
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.48,
|
| 146 |
+
"grad_norm": 8.991690635681152,
|
| 147 |
+
"learning_rate": 4.76e-05,
|
| 148 |
+
"loss": 0.7142,
|
| 149 |
+
"step": 120
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.504,
|
| 153 |
+
"grad_norm": 5.250122547149658,
|
| 154 |
+
"learning_rate": 5e-05,
|
| 155 |
+
"loss": 0.6461,
|
| 156 |
+
"step": 126
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.528,
|
| 160 |
+
"grad_norm": 6.273474216461182,
|
| 161 |
+
"learning_rate": 4.973333333333334e-05,
|
| 162 |
+
"loss": 0.6108,
|
| 163 |
+
"step": 132
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.552,
|
| 167 |
+
"grad_norm": 5.45080041885376,
|
| 168 |
+
"learning_rate": 4.9466666666666665e-05,
|
| 169 |
+
"loss": 0.5098,
|
| 170 |
+
"step": 138
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.576,
|
| 174 |
+
"grad_norm": 6.3116068840026855,
|
| 175 |
+
"learning_rate": 4.92e-05,
|
| 176 |
+
"loss": 0.4719,
|
| 177 |
+
"step": 144
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6,
|
| 181 |
+
"grad_norm": 9.022950172424316,
|
| 182 |
+
"learning_rate": 4.8933333333333335e-05,
|
| 183 |
+
"loss": 0.3653,
|
| 184 |
+
"step": 150
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.624,
|
| 188 |
+
"grad_norm": 6.852407455444336,
|
| 189 |
+
"learning_rate": 4.866666666666667e-05,
|
| 190 |
+
"loss": 0.4934,
|
| 191 |
+
"step": 156
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.648,
|
| 195 |
+
"grad_norm": 4.436535835266113,
|
| 196 |
+
"learning_rate": 4.8400000000000004e-05,
|
| 197 |
+
"loss": 0.3817,
|
| 198 |
+
"step": 162
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.672,
|
| 202 |
+
"grad_norm": 5.454000949859619,
|
| 203 |
+
"learning_rate": 4.8133333333333336e-05,
|
| 204 |
+
"loss": 0.3123,
|
| 205 |
+
"step": 168
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.696,
|
| 209 |
+
"grad_norm": 6.807215690612793,
|
| 210 |
+
"learning_rate": 4.7866666666666674e-05,
|
| 211 |
+
"loss": 0.2737,
|
| 212 |
+
"step": 174
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.72,
|
| 216 |
+
"grad_norm": 4.130777835845947,
|
| 217 |
+
"learning_rate": 4.76e-05,
|
| 218 |
+
"loss": 0.3287,
|
| 219 |
+
"step": 180
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.744,
|
| 223 |
+
"grad_norm": 15.173467636108398,
|
| 224 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 225 |
+
"loss": 0.2525,
|
| 226 |
+
"step": 186
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.768,
|
| 230 |
+
"grad_norm": 3.7970285415649414,
|
| 231 |
+
"learning_rate": 4.706666666666667e-05,
|
| 232 |
+
"loss": 0.3568,
|
| 233 |
+
"step": 192
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.792,
|
| 237 |
+
"grad_norm": 3.6102640628814697,
|
| 238 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 239 |
+
"loss": 0.2952,
|
| 240 |
+
"step": 198
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.816,
|
| 244 |
+
"grad_norm": 2.048801898956299,
|
| 245 |
+
"learning_rate": 4.653333333333334e-05,
|
| 246 |
+
"loss": 0.3303,
|
| 247 |
+
"step": 204
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.84,
|
| 251 |
+
"grad_norm": 9.570277214050293,
|
| 252 |
+
"learning_rate": 4.626666666666667e-05,
|
| 253 |
+
"loss": 0.2736,
|
| 254 |
+
"step": 210
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.864,
|
| 258 |
+
"grad_norm": 3.7270052433013916,
|
| 259 |
+
"learning_rate": 4.600000000000001e-05,
|
| 260 |
+
"loss": 0.2399,
|
| 261 |
+
"step": 216
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.888,
|
| 265 |
+
"grad_norm": 2.341561794281006,
|
| 266 |
+
"learning_rate": 4.573333333333333e-05,
|
| 267 |
+
"loss": 0.2085,
|
| 268 |
+
"step": 222
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.912,
|
| 272 |
+
"grad_norm": 3.1725029945373535,
|
| 273 |
+
"learning_rate": 4.546666666666667e-05,
|
| 274 |
+
"loss": 0.2126,
|
| 275 |
+
"step": 228
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.936,
|
| 279 |
+
"grad_norm": 9.990570068359375,
|
| 280 |
+
"learning_rate": 4.52e-05,
|
| 281 |
+
"loss": 0.2663,
|
| 282 |
+
"step": 234
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.96,
|
| 286 |
+
"grad_norm": 3.6300106048583984,
|
| 287 |
+
"learning_rate": 4.493333333333333e-05,
|
| 288 |
+
"loss": 0.2006,
|
| 289 |
+
"step": 240
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.984,
|
| 293 |
+
"grad_norm": 2.360503911972046,
|
| 294 |
+
"learning_rate": 4.466666666666667e-05,
|
| 295 |
+
"loss": 0.2727,
|
| 296 |
+
"step": 246
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.0,
|
| 300 |
+
"eval_accuracy": 0.9215,
|
| 301 |
+
"eval_f1_macro": 0.8995337377920993,
|
| 302 |
+
"eval_f1_micro": 0.9215,
|
| 303 |
+
"eval_f1_weighted": 0.9231309624099143,
|
| 304 |
+
"eval_loss": 0.23581676185131073,
|
| 305 |
+
"eval_precision_macro": 0.8849160410790557,
|
| 306 |
+
"eval_precision_micro": 0.9215,
|
| 307 |
+
"eval_precision_weighted": 0.9309033739712098,
|
| 308 |
+
"eval_recall_macro": 0.9233031833590024,
|
| 309 |
+
"eval_recall_micro": 0.9215,
|
| 310 |
+
"eval_recall_weighted": 0.9215,
|
| 311 |
+
"eval_runtime": 3.3949,
|
| 312 |
+
"eval_samples_per_second": 589.114,
|
| 313 |
+
"eval_steps_per_second": 4.713,
|
| 314 |
+
"step": 250
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.008,
|
| 318 |
+
"grad_norm": 4.654928684234619,
|
| 319 |
+
"learning_rate": 4.44e-05,
|
| 320 |
+
"loss": 0.2359,
|
| 321 |
+
"step": 252
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.032,
|
| 325 |
+
"grad_norm": 6.218105792999268,
|
| 326 |
+
"learning_rate": 4.417777777777778e-05,
|
| 327 |
+
"loss": 0.1733,
|
| 328 |
+
"step": 258
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.056,
|
| 332 |
+
"grad_norm": 5.516075611114502,
|
| 333 |
+
"learning_rate": 4.3911111111111116e-05,
|
| 334 |
+
"loss": 0.1447,
|
| 335 |
+
"step": 264
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.08,
|
| 339 |
+
"grad_norm": 5.734640598297119,
|
| 340 |
+
"learning_rate": 4.364444444444445e-05,
|
| 341 |
+
"loss": 0.1913,
|
| 342 |
+
"step": 270
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.104,
|
| 346 |
+
"grad_norm": 4.150918006896973,
|
| 347 |
+
"learning_rate": 4.337777777777778e-05,
|
| 348 |
+
"loss": 0.1179,
|
| 349 |
+
"step": 276
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.1280000000000001,
|
| 353 |
+
"grad_norm": 3.250934362411499,
|
| 354 |
+
"learning_rate": 4.311111111111111e-05,
|
| 355 |
+
"loss": 0.1777,
|
| 356 |
+
"step": 282
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.152,
|
| 360 |
+
"grad_norm": 4.020536422729492,
|
| 361 |
+
"learning_rate": 4.284444444444445e-05,
|
| 362 |
+
"loss": 0.2122,
|
| 363 |
+
"step": 288
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.176,
|
| 367 |
+
"grad_norm": 3.2493388652801514,
|
| 368 |
+
"learning_rate": 4.257777777777778e-05,
|
| 369 |
+
"loss": 0.2012,
|
| 370 |
+
"step": 294
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.2,
|
| 374 |
+
"grad_norm": 4.640542984008789,
|
| 375 |
+
"learning_rate": 4.231111111111111e-05,
|
| 376 |
+
"loss": 0.1433,
|
| 377 |
+
"step": 300
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.224,
|
| 381 |
+
"grad_norm": 3.5592172145843506,
|
| 382 |
+
"learning_rate": 4.204444444444445e-05,
|
| 383 |
+
"loss": 0.1534,
|
| 384 |
+
"step": 306
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.248,
|
| 388 |
+
"grad_norm": 5.752802848815918,
|
| 389 |
+
"learning_rate": 4.177777777777778e-05,
|
| 390 |
+
"loss": 0.1625,
|
| 391 |
+
"step": 312
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.272,
|
| 395 |
+
"grad_norm": 5.988048553466797,
|
| 396 |
+
"learning_rate": 4.151111111111111e-05,
|
| 397 |
+
"loss": 0.1654,
|
| 398 |
+
"step": 318
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.296,
|
| 402 |
+
"grad_norm": 3.1433417797088623,
|
| 403 |
+
"learning_rate": 4.124444444444444e-05,
|
| 404 |
+
"loss": 0.1507,
|
| 405 |
+
"step": 324
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.32,
|
| 409 |
+
"grad_norm": 2.363762617111206,
|
| 410 |
+
"learning_rate": 4.097777777777778e-05,
|
| 411 |
+
"loss": 0.1343,
|
| 412 |
+
"step": 330
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.3439999999999999,
|
| 416 |
+
"grad_norm": 2.4271459579467773,
|
| 417 |
+
"learning_rate": 4.071111111111111e-05,
|
| 418 |
+
"loss": 0.1354,
|
| 419 |
+
"step": 336
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.3679999999999999,
|
| 423 |
+
"grad_norm": 5.531872749328613,
|
| 424 |
+
"learning_rate": 4.0444444444444444e-05,
|
| 425 |
+
"loss": 0.2238,
|
| 426 |
+
"step": 342
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.392,
|
| 430 |
+
"grad_norm": 2.654528856277466,
|
| 431 |
+
"learning_rate": 4.017777777777778e-05,
|
| 432 |
+
"loss": 0.1248,
|
| 433 |
+
"step": 348
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.416,
|
| 437 |
+
"grad_norm": 2.4685096740722656,
|
| 438 |
+
"learning_rate": 3.9911111111111114e-05,
|
| 439 |
+
"loss": 0.142,
|
| 440 |
+
"step": 354
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.44,
|
| 444 |
+
"grad_norm": 11.145745277404785,
|
| 445 |
+
"learning_rate": 3.9644444444444445e-05,
|
| 446 |
+
"loss": 0.1379,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.464,
|
| 451 |
+
"grad_norm": 10.70506477355957,
|
| 452 |
+
"learning_rate": 3.937777777777778e-05,
|
| 453 |
+
"loss": 0.0927,
|
| 454 |
+
"step": 366
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.488,
|
| 458 |
+
"grad_norm": 1.3703113794326782,
|
| 459 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 460 |
+
"loss": 0.2147,
|
| 461 |
+
"step": 372
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.512,
|
| 465 |
+
"grad_norm": 2.9787039756774902,
|
| 466 |
+
"learning_rate": 3.8844444444444446e-05,
|
| 467 |
+
"loss": 0.1816,
|
| 468 |
+
"step": 378
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.536,
|
| 472 |
+
"grad_norm": 4.429356575012207,
|
| 473 |
+
"learning_rate": 3.857777777777778e-05,
|
| 474 |
+
"loss": 0.1271,
|
| 475 |
+
"step": 384
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.56,
|
| 479 |
+
"grad_norm": 2.4006407260894775,
|
| 480 |
+
"learning_rate": 3.8311111111111115e-05,
|
| 481 |
+
"loss": 0.1266,
|
| 482 |
+
"step": 390
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.584,
|
| 486 |
+
"grad_norm": 2.01302170753479,
|
| 487 |
+
"learning_rate": 3.804444444444445e-05,
|
| 488 |
+
"loss": 0.0847,
|
| 489 |
+
"step": 396
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.608,
|
| 493 |
+
"grad_norm": 2.242461681365967,
|
| 494 |
+
"learning_rate": 3.777777777777778e-05,
|
| 495 |
+
"loss": 0.1802,
|
| 496 |
+
"step": 402
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.6320000000000001,
|
| 500 |
+
"grad_norm": 1.8448535203933716,
|
| 501 |
+
"learning_rate": 3.7511111111111116e-05,
|
| 502 |
+
"loss": 0.1713,
|
| 503 |
+
"step": 408
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.6560000000000001,
|
| 507 |
+
"grad_norm": 2.21156907081604,
|
| 508 |
+
"learning_rate": 3.724444444444445e-05,
|
| 509 |
+
"loss": 0.1656,
|
| 510 |
+
"step": 414
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.6800000000000002,
|
| 514 |
+
"grad_norm": 4.768124580383301,
|
| 515 |
+
"learning_rate": 3.697777777777778e-05,
|
| 516 |
+
"loss": 0.1453,
|
| 517 |
+
"step": 420
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.704,
|
| 521 |
+
"grad_norm": 3.267815351486206,
|
| 522 |
+
"learning_rate": 3.671111111111111e-05,
|
| 523 |
+
"loss": 0.1755,
|
| 524 |
+
"step": 426
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.728,
|
| 528 |
+
"grad_norm": 1.797162652015686,
|
| 529 |
+
"learning_rate": 3.644444444444445e-05,
|
| 530 |
+
"loss": 0.1503,
|
| 531 |
+
"step": 432
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.752,
|
| 535 |
+
"grad_norm": 2.245846748352051,
|
| 536 |
+
"learning_rate": 3.617777777777778e-05,
|
| 537 |
+
"loss": 0.139,
|
| 538 |
+
"step": 438
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.776,
|
| 542 |
+
"grad_norm": 4.633366107940674,
|
| 543 |
+
"learning_rate": 3.591111111111111e-05,
|
| 544 |
+
"loss": 0.1298,
|
| 545 |
+
"step": 444
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.8,
|
| 549 |
+
"grad_norm": 4.398362636566162,
|
| 550 |
+
"learning_rate": 3.564444444444445e-05,
|
| 551 |
+
"loss": 0.1703,
|
| 552 |
+
"step": 450
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.8239999999999998,
|
| 556 |
+
"grad_norm": 4.176144599914551,
|
| 557 |
+
"learning_rate": 3.537777777777778e-05,
|
| 558 |
+
"loss": 0.1503,
|
| 559 |
+
"step": 456
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.8479999999999999,
|
| 563 |
+
"grad_norm": 6.216207027435303,
|
| 564 |
+
"learning_rate": 3.511111111111111e-05,
|
| 565 |
+
"loss": 0.1558,
|
| 566 |
+
"step": 462
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.8719999999999999,
|
| 570 |
+
"grad_norm": 2.794733762741089,
|
| 571 |
+
"learning_rate": 3.4844444444444444e-05,
|
| 572 |
+
"loss": 0.1679,
|
| 573 |
+
"step": 468
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.896,
|
| 577 |
+
"grad_norm": 6.9759392738342285,
|
| 578 |
+
"learning_rate": 3.457777777777778e-05,
|
| 579 |
+
"loss": 0.1304,
|
| 580 |
+
"step": 474
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.92,
|
| 584 |
+
"grad_norm": 1.3952761888504028,
|
| 585 |
+
"learning_rate": 3.431111111111111e-05,
|
| 586 |
+
"loss": 0.1418,
|
| 587 |
+
"step": 480
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.944,
|
| 591 |
+
"grad_norm": 1.8202506303787231,
|
| 592 |
+
"learning_rate": 3.4044444444444445e-05,
|
| 593 |
+
"loss": 0.1188,
|
| 594 |
+
"step": 486
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.968,
|
| 598 |
+
"grad_norm": 4.880939483642578,
|
| 599 |
+
"learning_rate": 3.377777777777778e-05,
|
| 600 |
+
"loss": 0.1252,
|
| 601 |
+
"step": 492
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.992,
|
| 605 |
+
"grad_norm": 1.7853918075561523,
|
| 606 |
+
"learning_rate": 3.3511111111111114e-05,
|
| 607 |
+
"loss": 0.1397,
|
| 608 |
+
"step": 498
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.0,
|
| 612 |
+
"eval_accuracy": 0.9395,
|
| 613 |
+
"eval_f1_macro": 0.9106849947356129,
|
| 614 |
+
"eval_f1_micro": 0.9395,
|
| 615 |
+
"eval_f1_weighted": 0.9383774262681576,
|
| 616 |
+
"eval_loss": 0.14122824370861053,
|
| 617 |
+
"eval_precision_macro": 0.9324340670283836,
|
| 618 |
+
"eval_precision_micro": 0.9395,
|
| 619 |
+
"eval_precision_weighted": 0.9408265963501754,
|
| 620 |
+
"eval_recall_macro": 0.8951750793370938,
|
| 621 |
+
"eval_recall_micro": 0.9395,
|
| 622 |
+
"eval_recall_weighted": 0.9395,
|
| 623 |
+
"eval_runtime": 3.4115,
|
| 624 |
+
"eval_samples_per_second": 586.256,
|
| 625 |
+
"eval_steps_per_second": 4.69,
|
| 626 |
+
"step": 500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.016,
|
| 630 |
+
"grad_norm": 3.5379767417907715,
|
| 631 |
+
"learning_rate": 3.3244444444444445e-05,
|
| 632 |
+
"loss": 0.1067,
|
| 633 |
+
"step": 504
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.04,
|
| 637 |
+
"grad_norm": 1.8406476974487305,
|
| 638 |
+
"learning_rate": 3.297777777777778e-05,
|
| 639 |
+
"loss": 0.1038,
|
| 640 |
+
"step": 510
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.064,
|
| 644 |
+
"grad_norm": 1.2835277318954468,
|
| 645 |
+
"learning_rate": 3.2711111111111115e-05,
|
| 646 |
+
"loss": 0.0894,
|
| 647 |
+
"step": 516
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.088,
|
| 651 |
+
"grad_norm": 0.9669094085693359,
|
| 652 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 653 |
+
"loss": 0.0914,
|
| 654 |
+
"step": 522
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.112,
|
| 658 |
+
"grad_norm": 1.4967998266220093,
|
| 659 |
+
"learning_rate": 3.217777777777778e-05,
|
| 660 |
+
"loss": 0.115,
|
| 661 |
+
"step": 528
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.136,
|
| 665 |
+
"grad_norm": 0.5459607243537903,
|
| 666 |
+
"learning_rate": 3.1911111111111116e-05,
|
| 667 |
+
"loss": 0.1238,
|
| 668 |
+
"step": 534
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.16,
|
| 672 |
+
"grad_norm": 0.6286458969116211,
|
| 673 |
+
"learning_rate": 3.164444444444444e-05,
|
| 674 |
+
"loss": 0.078,
|
| 675 |
+
"step": 540
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.184,
|
| 679 |
+
"grad_norm": 0.8293291926383972,
|
| 680 |
+
"learning_rate": 3.137777777777778e-05,
|
| 681 |
+
"loss": 0.0956,
|
| 682 |
+
"step": 546
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.208,
|
| 686 |
+
"grad_norm": 1.015953779220581,
|
| 687 |
+
"learning_rate": 3.111111111111111e-05,
|
| 688 |
+
"loss": 0.1022,
|
| 689 |
+
"step": 552
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.232,
|
| 693 |
+
"grad_norm": 0.6408522129058838,
|
| 694 |
+
"learning_rate": 3.084444444444445e-05,
|
| 695 |
+
"loss": 0.0839,
|
| 696 |
+
"step": 558
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.2560000000000002,
|
| 700 |
+
"grad_norm": 1.495943307876587,
|
| 701 |
+
"learning_rate": 3.057777777777778e-05,
|
| 702 |
+
"loss": 0.0937,
|
| 703 |
+
"step": 564
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.2800000000000002,
|
| 707 |
+
"grad_norm": 1.8174567222595215,
|
| 708 |
+
"learning_rate": 3.031111111111111e-05,
|
| 709 |
+
"loss": 0.1216,
|
| 710 |
+
"step": 570
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.304,
|
| 714 |
+
"grad_norm": 0.502436637878418,
|
| 715 |
+
"learning_rate": 3.004444444444445e-05,
|
| 716 |
+
"loss": 0.0754,
|
| 717 |
+
"step": 576
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.328,
|
| 721 |
+
"grad_norm": 5.995917320251465,
|
| 722 |
+
"learning_rate": 2.9777777777777777e-05,
|
| 723 |
+
"loss": 0.164,
|
| 724 |
+
"step": 582
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.352,
|
| 728 |
+
"grad_norm": 1.4363820552825928,
|
| 729 |
+
"learning_rate": 2.951111111111111e-05,
|
| 730 |
+
"loss": 0.1006,
|
| 731 |
+
"step": 588
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.376,
|
| 735 |
+
"grad_norm": 0.8328127861022949,
|
| 736 |
+
"learning_rate": 2.9244444444444446e-05,
|
| 737 |
+
"loss": 0.0861,
|
| 738 |
+
"step": 594
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.4,
|
| 742 |
+
"grad_norm": 0.8516309261322021,
|
| 743 |
+
"learning_rate": 2.897777777777778e-05,
|
| 744 |
+
"loss": 0.0852,
|
| 745 |
+
"step": 600
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.424,
|
| 749 |
+
"grad_norm": 1.308616042137146,
|
| 750 |
+
"learning_rate": 2.8711111111111113e-05,
|
| 751 |
+
"loss": 0.0785,
|
| 752 |
+
"step": 606
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.448,
|
| 756 |
+
"grad_norm": 2.7151458263397217,
|
| 757 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 758 |
+
"loss": 0.1236,
|
| 759 |
+
"step": 612
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.472,
|
| 763 |
+
"grad_norm": 0.8587580919265747,
|
| 764 |
+
"learning_rate": 2.8177777777777782e-05,
|
| 765 |
+
"loss": 0.0841,
|
| 766 |
+
"step": 618
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.496,
|
| 770 |
+
"grad_norm": 2.1243529319763184,
|
| 771 |
+
"learning_rate": 2.791111111111111e-05,
|
| 772 |
+
"loss": 0.0769,
|
| 773 |
+
"step": 624
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.52,
|
| 777 |
+
"grad_norm": 1.7264567613601685,
|
| 778 |
+
"learning_rate": 2.7644444444444445e-05,
|
| 779 |
+
"loss": 0.1453,
|
| 780 |
+
"step": 630
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.544,
|
| 784 |
+
"grad_norm": 0.745203971862793,
|
| 785 |
+
"learning_rate": 2.737777777777778e-05,
|
| 786 |
+
"loss": 0.0685,
|
| 787 |
+
"step": 636
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.568,
|
| 791 |
+
"grad_norm": 1.8616527318954468,
|
| 792 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 793 |
+
"loss": 0.1152,
|
| 794 |
+
"step": 642
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.592,
|
| 798 |
+
"grad_norm": 1.0319263935089111,
|
| 799 |
+
"learning_rate": 2.6844444444444446e-05,
|
| 800 |
+
"loss": 0.0866,
|
| 801 |
+
"step": 648
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.616,
|
| 805 |
+
"grad_norm": 1.321435809135437,
|
| 806 |
+
"learning_rate": 2.657777777777778e-05,
|
| 807 |
+
"loss": 0.0979,
|
| 808 |
+
"step": 654
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.64,
|
| 812 |
+
"grad_norm": 0.6810425519943237,
|
| 813 |
+
"learning_rate": 2.6311111111111115e-05,
|
| 814 |
+
"loss": 0.0746,
|
| 815 |
+
"step": 660
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.664,
|
| 819 |
+
"grad_norm": 4.602859020233154,
|
| 820 |
+
"learning_rate": 2.6044444444444443e-05,
|
| 821 |
+
"loss": 0.1134,
|
| 822 |
+
"step": 666
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.6879999999999997,
|
| 826 |
+
"grad_norm": 0.9797782301902771,
|
| 827 |
+
"learning_rate": 2.5777777777777778e-05,
|
| 828 |
+
"loss": 0.0779,
|
| 829 |
+
"step": 672
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.7119999999999997,
|
| 833 |
+
"grad_norm": 3.393965005874634,
|
| 834 |
+
"learning_rate": 2.5511111111111113e-05,
|
| 835 |
+
"loss": 0.1137,
|
| 836 |
+
"step": 678
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.7359999999999998,
|
| 840 |
+
"grad_norm": 1.6358873844146729,
|
| 841 |
+
"learning_rate": 2.5244444444444447e-05,
|
| 842 |
+
"loss": 0.0829,
|
| 843 |
+
"step": 684
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.76,
|
| 847 |
+
"grad_norm": 0.8677324056625366,
|
| 848 |
+
"learning_rate": 2.497777777777778e-05,
|
| 849 |
+
"loss": 0.0655,
|
| 850 |
+
"step": 690
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.784,
|
| 854 |
+
"grad_norm": 2.418769121170044,
|
| 855 |
+
"learning_rate": 2.4711111111111114e-05,
|
| 856 |
+
"loss": 0.0726,
|
| 857 |
+
"step": 696
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.808,
|
| 861 |
+
"grad_norm": 1.677323341369629,
|
| 862 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 863 |
+
"loss": 0.0694,
|
| 864 |
+
"step": 702
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.832,
|
| 868 |
+
"grad_norm": 1.2437670230865479,
|
| 869 |
+
"learning_rate": 2.417777777777778e-05,
|
| 870 |
+
"loss": 0.0986,
|
| 871 |
+
"step": 708
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.856,
|
| 875 |
+
"grad_norm": 2.447063684463501,
|
| 876 |
+
"learning_rate": 2.391111111111111e-05,
|
| 877 |
+
"loss": 0.1185,
|
| 878 |
+
"step": 714
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.88,
|
| 882 |
+
"grad_norm": 0.7579317092895508,
|
| 883 |
+
"learning_rate": 2.3644444444444446e-05,
|
| 884 |
+
"loss": 0.0932,
|
| 885 |
+
"step": 720
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.904,
|
| 889 |
+
"grad_norm": 1.1533098220825195,
|
| 890 |
+
"learning_rate": 2.337777777777778e-05,
|
| 891 |
+
"loss": 0.1013,
|
| 892 |
+
"step": 726
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.928,
|
| 896 |
+
"grad_norm": 0.8839074969291687,
|
| 897 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 898 |
+
"loss": 0.0912,
|
| 899 |
+
"step": 732
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.952,
|
| 903 |
+
"grad_norm": 1.182469129562378,
|
| 904 |
+
"learning_rate": 2.2844444444444447e-05,
|
| 905 |
+
"loss": 0.0901,
|
| 906 |
+
"step": 738
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.976,
|
| 910 |
+
"grad_norm": 0.9109925627708435,
|
| 911 |
+
"learning_rate": 2.2577777777777778e-05,
|
| 912 |
+
"loss": 0.0785,
|
| 913 |
+
"step": 744
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.0,
|
| 917 |
+
"grad_norm": 1.4611146450042725,
|
| 918 |
+
"learning_rate": 2.2311111111111113e-05,
|
| 919 |
+
"loss": 0.0768,
|
| 920 |
+
"step": 750
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.0,
|
| 924 |
+
"eval_accuracy": 0.942,
|
| 925 |
+
"eval_f1_macro": 0.9199698545563004,
|
| 926 |
+
"eval_f1_micro": 0.942,
|
| 927 |
+
"eval_f1_weighted": 0.942299793738485,
|
| 928 |
+
"eval_loss": 0.13686497509479523,
|
| 929 |
+
"eval_precision_macro": 0.912222911519835,
|
| 930 |
+
"eval_precision_micro": 0.942,
|
| 931 |
+
"eval_precision_weighted": 0.9429745034281065,
|
| 932 |
+
"eval_recall_macro": 0.9287782509639695,
|
| 933 |
+
"eval_recall_micro": 0.942,
|
| 934 |
+
"eval_recall_weighted": 0.942,
|
| 935 |
+
"eval_runtime": 3.3845,
|
| 936 |
+
"eval_samples_per_second": 590.924,
|
| 937 |
+
"eval_steps_per_second": 4.727,
|
| 938 |
+
"step": 750
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.024,
|
| 942 |
+
"grad_norm": 5.040261745452881,
|
| 943 |
+
"learning_rate": 2.2044444444444444e-05,
|
| 944 |
+
"loss": 0.078,
|
| 945 |
+
"step": 756
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.048,
|
| 949 |
+
"grad_norm": 0.5013237595558167,
|
| 950 |
+
"learning_rate": 2.177777777777778e-05,
|
| 951 |
+
"loss": 0.0558,
|
| 952 |
+
"step": 762
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.072,
|
| 956 |
+
"grad_norm": 1.1819310188293457,
|
| 957 |
+
"learning_rate": 2.1511111111111114e-05,
|
| 958 |
+
"loss": 0.0682,
|
| 959 |
+
"step": 768
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.096,
|
| 963 |
+
"grad_norm": 0.9416047930717468,
|
| 964 |
+
"learning_rate": 2.1244444444444445e-05,
|
| 965 |
+
"loss": 0.0775,
|
| 966 |
+
"step": 774
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.12,
|
| 970 |
+
"grad_norm": 2.0191128253936768,
|
| 971 |
+
"learning_rate": 2.097777777777778e-05,
|
| 972 |
+
"loss": 0.0645,
|
| 973 |
+
"step": 780
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.144,
|
| 977 |
+
"grad_norm": 3.3059170246124268,
|
| 978 |
+
"learning_rate": 2.071111111111111e-05,
|
| 979 |
+
"loss": 0.0713,
|
| 980 |
+
"step": 786
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.168,
|
| 984 |
+
"grad_norm": 0.6508151888847351,
|
| 985 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 986 |
+
"loss": 0.0631,
|
| 987 |
+
"step": 792
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 3.192,
|
| 991 |
+
"grad_norm": 0.7478683590888977,
|
| 992 |
+
"learning_rate": 2.0177777777777777e-05,
|
| 993 |
+
"loss": 0.0826,
|
| 994 |
+
"step": 798
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 3.216,
|
| 998 |
+
"grad_norm": 0.5315937995910645,
|
| 999 |
+
"learning_rate": 1.9911111111111112e-05,
|
| 1000 |
+
"loss": 0.0599,
|
| 1001 |
+
"step": 804
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.24,
|
| 1005 |
+
"grad_norm": 0.6902756690979004,
|
| 1006 |
+
"learning_rate": 1.9644444444444447e-05,
|
| 1007 |
+
"loss": 0.062,
|
| 1008 |
+
"step": 810
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.2640000000000002,
|
| 1012 |
+
"grad_norm": 2.4366424083709717,
|
| 1013 |
+
"learning_rate": 1.9377777777777778e-05,
|
| 1014 |
+
"loss": 0.0552,
|
| 1015 |
+
"step": 816
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 3.288,
|
| 1019 |
+
"grad_norm": 0.8592342734336853,
|
| 1020 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 1021 |
+
"loss": 0.0473,
|
| 1022 |
+
"step": 822
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.312,
|
| 1026 |
+
"grad_norm": 0.7974979877471924,
|
| 1027 |
+
"learning_rate": 1.8844444444444444e-05,
|
| 1028 |
+
"loss": 0.0843,
|
| 1029 |
+
"step": 828
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 3.336,
|
| 1033 |
+
"grad_norm": 0.6507941484451294,
|
| 1034 |
+
"learning_rate": 1.8577777777777776e-05,
|
| 1035 |
+
"loss": 0.0547,
|
| 1036 |
+
"step": 834
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.36,
|
| 1040 |
+
"grad_norm": 1.7816904783248901,
|
| 1041 |
+
"learning_rate": 1.8311111111111114e-05,
|
| 1042 |
+
"loss": 0.0734,
|
| 1043 |
+
"step": 840
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.384,
|
| 1047 |
+
"grad_norm": 2.3007311820983887,
|
| 1048 |
+
"learning_rate": 1.8044444444444445e-05,
|
| 1049 |
+
"loss": 0.1033,
|
| 1050 |
+
"step": 846
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.408,
|
| 1054 |
+
"grad_norm": 1.0759015083312988,
|
| 1055 |
+
"learning_rate": 1.777777777777778e-05,
|
| 1056 |
+
"loss": 0.0992,
|
| 1057 |
+
"step": 852
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 3.432,
|
| 1061 |
+
"grad_norm": 2.1372885704040527,
|
| 1062 |
+
"learning_rate": 1.751111111111111e-05,
|
| 1063 |
+
"loss": 0.0593,
|
| 1064 |
+
"step": 858
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.456,
|
| 1068 |
+
"grad_norm": 2.228823661804199,
|
| 1069 |
+
"learning_rate": 1.7244444444444446e-05,
|
| 1070 |
+
"loss": 0.0937,
|
| 1071 |
+
"step": 864
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 3.48,
|
| 1075 |
+
"grad_norm": 1.4194374084472656,
|
| 1076 |
+
"learning_rate": 1.6977777777777777e-05,
|
| 1077 |
+
"loss": 0.0667,
|
| 1078 |
+
"step": 870
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.504,
|
| 1082 |
+
"grad_norm": 0.7095490097999573,
|
| 1083 |
+
"learning_rate": 1.6711111111111112e-05,
|
| 1084 |
+
"loss": 0.0574,
|
| 1085 |
+
"step": 876
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 3.528,
|
| 1089 |
+
"grad_norm": 3.3914129734039307,
|
| 1090 |
+
"learning_rate": 1.6444444444444447e-05,
|
| 1091 |
+
"loss": 0.0969,
|
| 1092 |
+
"step": 882
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.552,
|
| 1096 |
+
"grad_norm": 1.8268787860870361,
|
| 1097 |
+
"learning_rate": 1.617777777777778e-05,
|
| 1098 |
+
"loss": 0.0716,
|
| 1099 |
+
"step": 888
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 3.576,
|
| 1103 |
+
"grad_norm": 1.4750251770019531,
|
| 1104 |
+
"learning_rate": 1.5911111111111113e-05,
|
| 1105 |
+
"loss": 0.0859,
|
| 1106 |
+
"step": 894
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.6,
|
| 1110 |
+
"grad_norm": 0.3522164523601532,
|
| 1111 |
+
"learning_rate": 1.5644444444444444e-05,
|
| 1112 |
+
"loss": 0.0505,
|
| 1113 |
+
"step": 900
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.624,
|
| 1117 |
+
"grad_norm": 1.7711290121078491,
|
| 1118 |
+
"learning_rate": 1.537777777777778e-05,
|
| 1119 |
+
"loss": 0.0571,
|
| 1120 |
+
"step": 906
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.648,
|
| 1124 |
+
"grad_norm": 1.3283618688583374,
|
| 1125 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 1126 |
+
"loss": 0.1006,
|
| 1127 |
+
"step": 912
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 3.672,
|
| 1131 |
+
"grad_norm": 2.121399402618408,
|
| 1132 |
+
"learning_rate": 1.4844444444444444e-05,
|
| 1133 |
+
"loss": 0.0838,
|
| 1134 |
+
"step": 918
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 3.6959999999999997,
|
| 1138 |
+
"grad_norm": 2.0860633850097656,
|
| 1139 |
+
"learning_rate": 1.4577777777777778e-05,
|
| 1140 |
+
"loss": 0.1117,
|
| 1141 |
+
"step": 924
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 3.7199999999999998,
|
| 1145 |
+
"grad_norm": 2.2945892810821533,
|
| 1146 |
+
"learning_rate": 1.4311111111111111e-05,
|
| 1147 |
+
"loss": 0.0727,
|
| 1148 |
+
"step": 930
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.7439999999999998,
|
| 1152 |
+
"grad_norm": 1.119083046913147,
|
| 1153 |
+
"learning_rate": 1.4044444444444446e-05,
|
| 1154 |
+
"loss": 0.0485,
|
| 1155 |
+
"step": 936
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.768,
|
| 1159 |
+
"grad_norm": 1.8427727222442627,
|
| 1160 |
+
"learning_rate": 1.3777777777777778e-05,
|
| 1161 |
+
"loss": 0.0574,
|
| 1162 |
+
"step": 942
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 3.792,
|
| 1166 |
+
"grad_norm": 1.5588749647140503,
|
| 1167 |
+
"learning_rate": 1.351111111111111e-05,
|
| 1168 |
+
"loss": 0.0784,
|
| 1169 |
+
"step": 948
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 3.816,
|
| 1173 |
+
"grad_norm": 1.580621361732483,
|
| 1174 |
+
"learning_rate": 1.3244444444444445e-05,
|
| 1175 |
+
"loss": 0.054,
|
| 1176 |
+
"step": 954
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 3.84,
|
| 1180 |
+
"grad_norm": 4.9234843254089355,
|
| 1181 |
+
"learning_rate": 1.2977777777777777e-05,
|
| 1182 |
+
"loss": 0.0976,
|
| 1183 |
+
"step": 960
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 3.864,
|
| 1187 |
+
"grad_norm": 1.1440095901489258,
|
| 1188 |
+
"learning_rate": 1.2711111111111113e-05,
|
| 1189 |
+
"loss": 0.0586,
|
| 1190 |
+
"step": 966
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.888,
|
| 1194 |
+
"grad_norm": 1.0315749645233154,
|
| 1195 |
+
"learning_rate": 1.2444444444444445e-05,
|
| 1196 |
+
"loss": 0.0693,
|
| 1197 |
+
"step": 972
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.912,
|
| 1201 |
+
"grad_norm": 1.4318304061889648,
|
| 1202 |
+
"learning_rate": 1.2177777777777778e-05,
|
| 1203 |
+
"loss": 0.069,
|
| 1204 |
+
"step": 978
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 3.936,
|
| 1208 |
+
"grad_norm": 2.342024087905884,
|
| 1209 |
+
"learning_rate": 1.1911111111111112e-05,
|
| 1210 |
+
"loss": 0.0815,
|
| 1211 |
+
"step": 984
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 3.96,
|
| 1215 |
+
"grad_norm": 1.2760955095291138,
|
| 1216 |
+
"learning_rate": 1.1644444444444446e-05,
|
| 1217 |
+
"loss": 0.07,
|
| 1218 |
+
"step": 990
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 3.984,
|
| 1222 |
+
"grad_norm": 1.5678285360336304,
|
| 1223 |
+
"learning_rate": 1.1377777777777779e-05,
|
| 1224 |
+
"loss": 0.0795,
|
| 1225 |
+
"step": 996
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 4.0,
|
| 1229 |
+
"eval_accuracy": 0.943,
|
| 1230 |
+
"eval_f1_macro": 0.9169826832623412,
|
| 1231 |
+
"eval_f1_micro": 0.943,
|
| 1232 |
+
"eval_f1_weighted": 0.9427985114313238,
|
| 1233 |
+
"eval_loss": 0.13341853022575378,
|
| 1234 |
+
"eval_precision_macro": 0.9227534317185495,
|
| 1235 |
+
"eval_precision_micro": 0.943,
|
| 1236 |
+
"eval_precision_weighted": 0.9430912986498113,
|
| 1237 |
+
"eval_recall_macro": 0.9119580961776227,
|
| 1238 |
+
"eval_recall_micro": 0.943,
|
| 1239 |
+
"eval_recall_weighted": 0.943,
|
| 1240 |
+
"eval_runtime": 3.3617,
|
| 1241 |
+
"eval_samples_per_second": 594.941,
|
| 1242 |
+
"eval_steps_per_second": 4.76,
|
| 1243 |
+
"step": 1000
|
| 1244 |
+
}
|
| 1245 |
+
],
|
| 1246 |
+
"logging_steps": 6,
|
| 1247 |
+
"max_steps": 1250,
|
| 1248 |
+
"num_input_tokens_seen": 0,
|
| 1249 |
+
"num_train_epochs": 5,
|
| 1250 |
+
"save_steps": 500,
|
| 1251 |
+
"stateful_callbacks": {
|
| 1252 |
+
"EarlyStoppingCallback": {
|
| 1253 |
+
"args": {
|
| 1254 |
+
"early_stopping_patience": 5,
|
| 1255 |
+
"early_stopping_threshold": 0.01
|
| 1256 |
+
},
|
| 1257 |
+
"attributes": {
|
| 1258 |
+
"early_stopping_patience_counter": 2
|
| 1259 |
+
}
|
| 1260 |
+
},
|
| 1261 |
+
"TrainerControl": {
|
| 1262 |
+
"args": {
|
| 1263 |
+
"should_epoch_stop": false,
|
| 1264 |
+
"should_evaluate": false,
|
| 1265 |
+
"should_log": false,
|
| 1266 |
+
"should_save": true,
|
| 1267 |
+
"should_training_stop": false
|
| 1268 |
+
},
|
| 1269 |
+
"attributes": {}
|
| 1270 |
+
}
|
| 1271 |
+
},
|
| 1272 |
+
"total_flos": 4209928077312000.0,
|
| 1273 |
+
"train_batch_size": 64,
|
| 1274 |
+
"trial_name": null,
|
| 1275 |
+
"trial_params": null
|
| 1276 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e75ceb3da2420026e58517286528dc020715923e2f876ec81846263ae8ec8cf7
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
| 3 |
+
"_num_labels": 6,
|
| 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": "sadness",
|
| 15 |
+
"1": "joy",
|
| 16 |
+
"2": "love",
|
| 17 |
+
"3": "anger",
|
| 18 |
+
"4": "fear",
|
| 19 |
+
"5": "surprise"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"anger": 3,
|
| 25 |
+
"fear": 4,
|
| 26 |
+
"joy": 1,
|
| 27 |
+
"love": 2,
|
| 28 |
+
"sadness": 0,
|
| 29 |
+
"surprise": 5
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "bert",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.47.1",
|
| 41 |
+
"type_vocab_size": 2,
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 30522
|
| 44 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c23242b997142673a26c3d533fe71e0f8559f2ec9d26881534cf0619171bff5e
|
| 3 |
+
size 437970952
|
runs/Jan13_14-38-13_r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1/events.out.tfevents.1736779095.r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1.71.0
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 sha256:3f25504a93622d924d29099bccc517e6076be1ca03174ef1638b09bca07f984f
|
| 3 |
+
size 53682
|
runs/Jan13_14-38-13_r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1/events.out.tfevents.1736779539.r-xuehangcang-autotrain-clnd3b3t-bb6c0-gh8i1.71.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00026af3aea5dac2bf8523b3a47afa5543050ea174e94ae351f11ffc11807e23
|
| 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:e75ceb3da2420026e58517286528dc020715923e2f876ec81846263ae8ec8cf7
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "dair-ai/emotion",
|
| 3 |
+
"model": "google-bert/bert-base-uncased",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 5,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 64,
|
| 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": "text",
|
| 18 |
+
"target_column": "label",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "Emotion-Classification",
|
| 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": "XuehangCang",
|
| 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
|
|
|