Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-60/config.json +42 -0
- checkpoint-60/model.safetensors +3 -0
- checkpoint-60/optimizer.pt +3 -0
- checkpoint-60/rng_state.pth +3 -0
- checkpoint-60/scheduler.pt +3 -0
- checkpoint-60/trainer_state.json +516 -0
- checkpoint-60/training_args.bin +3 -0
- config.json +42 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jan13_09-17-26_r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf/events.out.tfevents.1736759848.r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf.129.0 +2 -2
- runs/Jan13_09-17-26_r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf/events.out.tfevents.1736760055.r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf.129.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: michellejieli/emotion_text_classifier
|
| 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: 0.008126698434352875
|
| 17 |
+
|
| 18 |
+
f1_macro: 1.0
|
| 19 |
+
|
| 20 |
+
f1_micro: 1.0
|
| 21 |
+
|
| 22 |
+
f1_weighted: 1.0
|
| 23 |
+
|
| 24 |
+
precision_macro: 1.0
|
| 25 |
+
|
| 26 |
+
precision_micro: 1.0
|
| 27 |
+
|
| 28 |
+
precision_weighted: 1.0
|
| 29 |
+
|
| 30 |
+
recall_macro: 1.0
|
| 31 |
+
|
| 32 |
+
recall_micro: 1.0
|
| 33 |
+
|
| 34 |
+
recall_weighted: 1.0
|
| 35 |
+
|
| 36 |
+
accuracy: 1.0
|
checkpoint-60/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "michellejieli/emotion_text_classifier",
|
| 3 |
+
"_num_labels": 4,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "Angry",
|
| 17 |
+
"1": "Danger",
|
| 18 |
+
"2": "Joy",
|
| 19 |
+
"3": "Neutral"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"Angry": 0,
|
| 25 |
+
"Danger": 1,
|
| 26 |
+
"Joy": 2,
|
| 27 |
+
"Neutral": 3
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-05,
|
| 30 |
+
"max_position_embeddings": 514,
|
| 31 |
+
"model_type": "roberta",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 6,
|
| 34 |
+
"pad_token_id": 1,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.47.1",
|
| 39 |
+
"type_vocab_size": 1,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 50265
|
| 42 |
+
}
|
checkpoint-60/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82e14e80fa3097b7f14941b8433231ab4c9e3ad47fc9f0f4ef8362418f839295
|
| 3 |
+
size 328498432
|
checkpoint-60/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13e7b132f60c80f58e79f2d8aad975936963918a515041814f7bbdda67a96d6d
|
| 3 |
+
size 657056954
|
checkpoint-60/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b70fce68775a4688a6522f9d8ec32742a7ce1deb8eac400b12aafee5ad1510
|
| 3 |
+
size 13990
|
checkpoint-60/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:974fb60062a9e094d57046984954545b807c1053a95415c6cb8cd6fd59c288ae
|
| 3 |
+
size 1064
|
checkpoint-60/trainer_state.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.008126698434352875,
|
| 3 |
+
"best_model_checkpoint": "moretrained/checkpoint-60",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 8.041182518005371,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 1.2425,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 10.465538024902344,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 1.4105,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 8.195067405700684,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 1.4073,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 8.528489112854004,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 1.2445,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 8.401679039001465,
|
| 42 |
+
"learning_rate": 4.166666666666667e-05,
|
| 43 |
+
"loss": 1.1273,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 6.660462856292725,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 1.1498,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 7.276221752166748,
|
| 56 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 57 |
+
"loss": 1.1399,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 7.235668659210205,
|
| 63 |
+
"learning_rate": 4.814814814814815e-05,
|
| 64 |
+
"loss": 0.8281,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 8.097387313842773,
|
| 70 |
+
"learning_rate": 4.722222222222222e-05,
|
| 71 |
+
"loss": 1.0547,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 5.169978618621826,
|
| 77 |
+
"learning_rate": 4.62962962962963e-05,
|
| 78 |
+
"loss": 0.7334,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 6.120723724365234,
|
| 84 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 85 |
+
"loss": 0.7317,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 5.884712219238281,
|
| 91 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 92 |
+
"loss": 0.6495,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 4.4953131675720215,
|
| 98 |
+
"learning_rate": 4.351851851851852e-05,
|
| 99 |
+
"loss": 0.4685,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 7.683829307556152,
|
| 105 |
+
"learning_rate": 4.259259259259259e-05,
|
| 106 |
+
"loss": 0.604,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 5.053662300109863,
|
| 112 |
+
"learning_rate": 4.166666666666667e-05,
|
| 113 |
+
"loss": 0.4217,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 4.671836853027344,
|
| 119 |
+
"learning_rate": 4.074074074074074e-05,
|
| 120 |
+
"loss": 0.4657,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 3.610461473464966,
|
| 126 |
+
"learning_rate": 3.981481481481482e-05,
|
| 127 |
+
"loss": 0.323,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 3.969586133956909,
|
| 133 |
+
"learning_rate": 3.888888888888889e-05,
|
| 134 |
+
"loss": 0.2853,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 2.483790874481201,
|
| 140 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 141 |
+
"loss": 0.2004,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 3.320207357406616,
|
| 147 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 148 |
+
"loss": 0.2619,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 1.0,
|
| 154 |
+
"eval_f1_macro": 1.0,
|
| 155 |
+
"eval_f1_micro": 1.0,
|
| 156 |
+
"eval_f1_weighted": 1.0,
|
| 157 |
+
"eval_loss": 0.13431890308856964,
|
| 158 |
+
"eval_precision_macro": 1.0,
|
| 159 |
+
"eval_precision_micro": 1.0,
|
| 160 |
+
"eval_precision_weighted": 1.0,
|
| 161 |
+
"eval_recall_macro": 1.0,
|
| 162 |
+
"eval_recall_micro": 1.0,
|
| 163 |
+
"eval_recall_weighted": 1.0,
|
| 164 |
+
"eval_runtime": 3.4405,
|
| 165 |
+
"eval_samples_per_second": 11.626,
|
| 166 |
+
"eval_steps_per_second": 0.872,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.05,
|
| 171 |
+
"grad_norm": 2.5963408946990967,
|
| 172 |
+
"learning_rate": 3.611111111111111e-05,
|
| 173 |
+
"loss": 0.209,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.1,
|
| 178 |
+
"grad_norm": 2.093904972076416,
|
| 179 |
+
"learning_rate": 3.518518518518519e-05,
|
| 180 |
+
"loss": 0.1631,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.15,
|
| 185 |
+
"grad_norm": 1.764503002166748,
|
| 186 |
+
"learning_rate": 3.425925925925926e-05,
|
| 187 |
+
"loss": 0.1211,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.2,
|
| 192 |
+
"grad_norm": 1.8142845630645752,
|
| 193 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 194 |
+
"loss": 0.1314,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.25,
|
| 199 |
+
"grad_norm": 1.1502163410186768,
|
| 200 |
+
"learning_rate": 3.240740740740741e-05,
|
| 201 |
+
"loss": 0.0937,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.3,
|
| 206 |
+
"grad_norm": 1.2658973932266235,
|
| 207 |
+
"learning_rate": 3.148148148148148e-05,
|
| 208 |
+
"loss": 0.095,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.35,
|
| 213 |
+
"grad_norm": 0.9761741757392883,
|
| 214 |
+
"learning_rate": 3.055555555555556e-05,
|
| 215 |
+
"loss": 0.0711,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.4,
|
| 220 |
+
"grad_norm": 1.0011101961135864,
|
| 221 |
+
"learning_rate": 2.962962962962963e-05,
|
| 222 |
+
"loss": 0.0629,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.45,
|
| 227 |
+
"grad_norm": 0.8154647946357727,
|
| 228 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 229 |
+
"loss": 0.0532,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.5,
|
| 234 |
+
"grad_norm": 0.6326289772987366,
|
| 235 |
+
"learning_rate": 2.777777777777778e-05,
|
| 236 |
+
"loss": 0.046,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.55,
|
| 241 |
+
"grad_norm": 0.4778478741645813,
|
| 242 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 243 |
+
"loss": 0.0396,
|
| 244 |
+
"step": 31
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.6,
|
| 248 |
+
"grad_norm": 0.54181969165802,
|
| 249 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 250 |
+
"loss": 0.0435,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.65,
|
| 255 |
+
"grad_norm": 0.5311982035636902,
|
| 256 |
+
"learning_rate": 2.5e-05,
|
| 257 |
+
"loss": 0.0361,
|
| 258 |
+
"step": 33
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.7,
|
| 262 |
+
"grad_norm": 0.7593758702278137,
|
| 263 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 264 |
+
"loss": 0.0388,
|
| 265 |
+
"step": 34
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.75,
|
| 269 |
+
"grad_norm": 0.36655837297439575,
|
| 270 |
+
"learning_rate": 2.314814814814815e-05,
|
| 271 |
+
"loss": 0.0288,
|
| 272 |
+
"step": 35
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.8,
|
| 276 |
+
"grad_norm": 0.3227110803127289,
|
| 277 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 278 |
+
"loss": 0.0242,
|
| 279 |
+
"step": 36
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.85,
|
| 283 |
+
"grad_norm": 0.40935859084129333,
|
| 284 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 285 |
+
"loss": 0.0265,
|
| 286 |
+
"step": 37
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.9,
|
| 290 |
+
"grad_norm": 0.30335429310798645,
|
| 291 |
+
"learning_rate": 2.037037037037037e-05,
|
| 292 |
+
"loss": 0.0232,
|
| 293 |
+
"step": 38
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.95,
|
| 297 |
+
"grad_norm": 0.31546491384506226,
|
| 298 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 299 |
+
"loss": 0.0225,
|
| 300 |
+
"step": 39
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.0,
|
| 304 |
+
"grad_norm": 0.3101823031902313,
|
| 305 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 306 |
+
"loss": 0.0199,
|
| 307 |
+
"step": 40
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.0,
|
| 311 |
+
"eval_accuracy": 1.0,
|
| 312 |
+
"eval_f1_macro": 1.0,
|
| 313 |
+
"eval_f1_micro": 1.0,
|
| 314 |
+
"eval_f1_weighted": 1.0,
|
| 315 |
+
"eval_loss": 0.012671445496380329,
|
| 316 |
+
"eval_precision_macro": 1.0,
|
| 317 |
+
"eval_precision_micro": 1.0,
|
| 318 |
+
"eval_precision_weighted": 1.0,
|
| 319 |
+
"eval_recall_macro": 1.0,
|
| 320 |
+
"eval_recall_micro": 1.0,
|
| 321 |
+
"eval_recall_weighted": 1.0,
|
| 322 |
+
"eval_runtime": 3.5651,
|
| 323 |
+
"eval_samples_per_second": 11.22,
|
| 324 |
+
"eval_steps_per_second": 0.841,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.05,
|
| 329 |
+
"grad_norm": 0.2425149530172348,
|
| 330 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 331 |
+
"loss": 0.0185,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.1,
|
| 336 |
+
"grad_norm": 0.19967606663703918,
|
| 337 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 338 |
+
"loss": 0.0161,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.15,
|
| 343 |
+
"grad_norm": 0.20470941066741943,
|
| 344 |
+
"learning_rate": 1.574074074074074e-05,
|
| 345 |
+
"loss": 0.0153,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.2,
|
| 350 |
+
"grad_norm": 0.23414605855941772,
|
| 351 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 352 |
+
"loss": 0.017,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.25,
|
| 357 |
+
"grad_norm": 0.22393330931663513,
|
| 358 |
+
"learning_rate": 1.388888888888889e-05,
|
| 359 |
+
"loss": 0.0158,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.3,
|
| 364 |
+
"grad_norm": 0.17999465763568878,
|
| 365 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 366 |
+
"loss": 0.0139,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.35,
|
| 371 |
+
"grad_norm": 0.1812359243631363,
|
| 372 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 373 |
+
"loss": 0.0145,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.4,
|
| 378 |
+
"grad_norm": 0.1997949630022049,
|
| 379 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 380 |
+
"loss": 0.0158,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.45,
|
| 385 |
+
"grad_norm": 0.19273602962493896,
|
| 386 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 387 |
+
"loss": 0.0128,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.5,
|
| 392 |
+
"grad_norm": 0.1569110006093979,
|
| 393 |
+
"learning_rate": 9.259259259259259e-06,
|
| 394 |
+
"loss": 0.0123,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.55,
|
| 399 |
+
"grad_norm": 0.280518114566803,
|
| 400 |
+
"learning_rate": 8.333333333333334e-06,
|
| 401 |
+
"loss": 0.0164,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.6,
|
| 406 |
+
"grad_norm": 0.17345570027828217,
|
| 407 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 408 |
+
"loss": 0.0129,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.65,
|
| 413 |
+
"grad_norm": 0.1595950424671173,
|
| 414 |
+
"learning_rate": 6.481481481481481e-06,
|
| 415 |
+
"loss": 0.0134,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.7,
|
| 420 |
+
"grad_norm": 0.18685200810432434,
|
| 421 |
+
"learning_rate": 5.555555555555556e-06,
|
| 422 |
+
"loss": 0.0133,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.75,
|
| 427 |
+
"grad_norm": 0.17671343684196472,
|
| 428 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 429 |
+
"loss": 0.0132,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.8,
|
| 434 |
+
"grad_norm": 0.16518476605415344,
|
| 435 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 436 |
+
"loss": 0.0121,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.85,
|
| 441 |
+
"grad_norm": 0.1776934117078781,
|
| 442 |
+
"learning_rate": 2.777777777777778e-06,
|
| 443 |
+
"loss": 0.0125,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.9,
|
| 448 |
+
"grad_norm": 0.18373462557792664,
|
| 449 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 450 |
+
"loss": 0.0142,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.95,
|
| 455 |
+
"grad_norm": 0.14108715951442719,
|
| 456 |
+
"learning_rate": 9.259259259259259e-07,
|
| 457 |
+
"loss": 0.011,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.0,
|
| 462 |
+
"grad_norm": 0.1863107532262802,
|
| 463 |
+
"learning_rate": 0.0,
|
| 464 |
+
"loss": 0.0129,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.0,
|
| 469 |
+
"eval_accuracy": 1.0,
|
| 470 |
+
"eval_f1_macro": 1.0,
|
| 471 |
+
"eval_f1_micro": 1.0,
|
| 472 |
+
"eval_f1_weighted": 1.0,
|
| 473 |
+
"eval_loss": 0.008126698434352875,
|
| 474 |
+
"eval_precision_macro": 1.0,
|
| 475 |
+
"eval_precision_micro": 1.0,
|
| 476 |
+
"eval_precision_weighted": 1.0,
|
| 477 |
+
"eval_recall_macro": 1.0,
|
| 478 |
+
"eval_recall_micro": 1.0,
|
| 479 |
+
"eval_recall_weighted": 1.0,
|
| 480 |
+
"eval_runtime": 3.4978,
|
| 481 |
+
"eval_samples_per_second": 11.436,
|
| 482 |
+
"eval_steps_per_second": 0.858,
|
| 483 |
+
"step": 60
|
| 484 |
+
}
|
| 485 |
+
],
|
| 486 |
+
"logging_steps": 1,
|
| 487 |
+
"max_steps": 60,
|
| 488 |
+
"num_input_tokens_seen": 0,
|
| 489 |
+
"num_train_epochs": 3,
|
| 490 |
+
"save_steps": 500,
|
| 491 |
+
"stateful_callbacks": {
|
| 492 |
+
"EarlyStoppingCallback": {
|
| 493 |
+
"args": {
|
| 494 |
+
"early_stopping_patience": 5,
|
| 495 |
+
"early_stopping_threshold": 0.01
|
| 496 |
+
},
|
| 497 |
+
"attributes": {
|
| 498 |
+
"early_stopping_patience_counter": 1
|
| 499 |
+
}
|
| 500 |
+
},
|
| 501 |
+
"TrainerControl": {
|
| 502 |
+
"args": {
|
| 503 |
+
"should_epoch_stop": false,
|
| 504 |
+
"should_evaluate": false,
|
| 505 |
+
"should_log": false,
|
| 506 |
+
"should_save": true,
|
| 507 |
+
"should_training_stop": true
|
| 508 |
+
},
|
| 509 |
+
"attributes": {}
|
| 510 |
+
}
|
| 511 |
+
},
|
| 512 |
+
"total_flos": 15896654807040.0,
|
| 513 |
+
"train_batch_size": 8,
|
| 514 |
+
"trial_name": null,
|
| 515 |
+
"trial_params": null
|
| 516 |
+
}
|
checkpoint-60/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6aeee0e05ee8a3075107393829e7329a95f66ccbf2d3cca66dc4fccbd3e731d
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "michellejieli/emotion_text_classifier",
|
| 3 |
+
"_num_labels": 4,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "Angry",
|
| 17 |
+
"1": "Danger",
|
| 18 |
+
"2": "Joy",
|
| 19 |
+
"3": "Neutral"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"Angry": 0,
|
| 25 |
+
"Danger": 1,
|
| 26 |
+
"Joy": 2,
|
| 27 |
+
"Neutral": 3
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-05,
|
| 30 |
+
"max_position_embeddings": 514,
|
| 31 |
+
"model_type": "roberta",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 6,
|
| 34 |
+
"pad_token_id": 1,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.47.1",
|
| 39 |
+
"type_vocab_size": 1,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 50265
|
| 42 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82e14e80fa3097b7f14941b8433231ab4c9e3ad47fc9f0f4ef8362418f839295
|
| 3 |
+
size 328498432
|
runs/Jan13_09-17-26_r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf/events.out.tfevents.1736759848.r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf.129.0
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:c0ef7629a41619ce87a104ca4fe4cc39a4531f5b7d838a0e1ecdeadfc8525f8d
|
| 3 |
+
size 20633
|
runs/Jan13_09-17-26_r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf/events.out.tfevents.1736760055.r-thedarktechie-sentianalysisone-4ziicw59-9f507-prcpf.129.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:925ac40927be6129d6cf1f64d225078e2080fc8907d20deae5011daea16f6a53
|
| 3 |
+
size 906
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"max_length": 512,
|
| 53 |
+
"model_max_length": 512,
|
| 54 |
+
"pad_to_multiple_of": null,
|
| 55 |
+
"pad_token": "<pad>",
|
| 56 |
+
"pad_token_type_id": 0,
|
| 57 |
+
"padding_side": "right",
|
| 58 |
+
"sep_token": "</s>",
|
| 59 |
+
"stride": 0,
|
| 60 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 61 |
+
"trim_offsets": true,
|
| 62 |
+
"truncation_side": "right",
|
| 63 |
+
"truncation_strategy": "longest_first",
|
| 64 |
+
"unk_token": "<unk>"
|
| 65 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6aeee0e05ee8a3075107393829e7329a95f66ccbf2d3cca66dc4fccbd3e731d
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "moretrained/autotrain-data",
|
| 3 |
+
"model": "michellejieli/emotion_text_classifier",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 8,
|
| 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": "moretrained",
|
| 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": "thedarktechie",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|