Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-32895/config.json +38 -0
- checkpoint-32895/model.safetensors +3 -0
- checkpoint-32895/optimizer.pt +3 -0
- checkpoint-32895/rng_state.pth +3 -0
- checkpoint-32895/scheduler.pt +3 -0
- checkpoint-32895/trainer_state.json +480 -0
- checkpoint-32895/training_args.bin +3 -0
- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- autotrain-8s6z2-1g2hg/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.1894965022802353
|
| 18 |
+
|
| 19 |
+
f1: 0.9633213150168105
|
| 20 |
+
|
| 21 |
+
precision: 0.9603846270512937
|
| 22 |
+
|
| 23 |
+
recall: 0.9662760178233535
|
| 24 |
+
|
| 25 |
+
auc: 0.9812675754686511
|
| 26 |
+
|
| 27 |
+
accuracy: 0.945028386420119
|
checkpoint-32895/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-irony",
|
| 3 |
+
"_num_labels": 2,
|
| 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": "objective",
|
| 17 |
+
"1": "subjective"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"objective": 0,
|
| 23 |
+
"subjective": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.38.2",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
checkpoint-32895/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8f49a8ffc04c3b84a4598c60063878faf5b7e8095ad4c640b00fd111bb5e7e8
|
| 3 |
+
size 498612824
|
checkpoint-32895/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b11ea74e7e3d11d467b940f431f34fdd25671e7da8e0dad8e78697d3d137ca76
|
| 3 |
+
size 997345530
|
checkpoint-32895/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31eec3cb55c5782e2294a9d5ab36446f81961cf57af52296164cded412d0c063
|
| 3 |
+
size 14244
|
checkpoint-32895/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a78cd4bac48016fc1d6546504fec20b85960dc04117165a2058b205f9fc89cb1
|
| 3 |
+
size 1064
|
checkpoint-32895/trainer_state.json
ADDED
|
@@ -0,0 +1,480 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1894965022802353,
|
| 3 |
+
"best_model_checkpoint": "autotrain-8s6z2-1g2hg/checkpoint-32895",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 32895,
|
| 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": 3.4229037761688232,
|
| 14 |
+
"learning_rate": 8.282674772036476e-06,
|
| 15 |
+
"loss": 0.655,
|
| 16 |
+
"step": 548
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 2.956129789352417,
|
| 21 |
+
"learning_rate": 1.661094224924012e-05,
|
| 22 |
+
"loss": 0.5579,
|
| 23 |
+
"step": 1096
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 7.492773056030273,
|
| 28 |
+
"learning_rate": 2.493920972644377e-05,
|
| 29 |
+
"loss": 0.4886,
|
| 30 |
+
"step": 1644
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 9.447515487670898,
|
| 35 |
+
"learning_rate": 3.326747720364742e-05,
|
| 36 |
+
"loss": 0.4206,
|
| 37 |
+
"step": 2192
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 10.904797554016113,
|
| 42 |
+
"learning_rate": 4.158054711246201e-05,
|
| 43 |
+
"loss": 0.4038,
|
| 44 |
+
"step": 2740
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 8.469663619995117,
|
| 49 |
+
"learning_rate": 4.9908814589665656e-05,
|
| 50 |
+
"loss": 0.3769,
|
| 51 |
+
"step": 3288
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 6.261867046356201,
|
| 56 |
+
"learning_rate": 4.9086302989359904e-05,
|
| 57 |
+
"loss": 0.3841,
|
| 58 |
+
"step": 3836
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 4.032571792602539,
|
| 63 |
+
"learning_rate": 4.8160783651410236e-05,
|
| 64 |
+
"loss": 0.3391,
|
| 65 |
+
"step": 4384
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 48.33228302001953,
|
| 70 |
+
"learning_rate": 4.723526431346057e-05,
|
| 71 |
+
"loss": 0.3192,
|
| 72 |
+
"step": 4932
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 4.632198810577393,
|
| 77 |
+
"learning_rate": 4.630974497551089e-05,
|
| 78 |
+
"loss": 0.3239,
|
| 79 |
+
"step": 5480
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 2.5730295181274414,
|
| 84 |
+
"learning_rate": 4.5384225637561225e-05,
|
| 85 |
+
"loss": 0.3143,
|
| 86 |
+
"step": 6028
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 3.378683090209961,
|
| 91 |
+
"learning_rate": 4.446208410741429e-05,
|
| 92 |
+
"loss": 0.3059,
|
| 93 |
+
"step": 6576
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 10.585208892822266,
|
| 98 |
+
"learning_rate": 4.353656476946462e-05,
|
| 99 |
+
"loss": 0.2987,
|
| 100 |
+
"step": 7124
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 16.021188735961914,
|
| 105 |
+
"learning_rate": 4.261104543151495e-05,
|
| 106 |
+
"loss": 0.2935,
|
| 107 |
+
"step": 7672
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 2.585524797439575,
|
| 112 |
+
"learning_rate": 4.168552609356528e-05,
|
| 113 |
+
"loss": 0.292,
|
| 114 |
+
"step": 8220
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 0.8300177454948425,
|
| 119 |
+
"learning_rate": 4.0761695659516976e-05,
|
| 120 |
+
"loss": 0.2746,
|
| 121 |
+
"step": 8768
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 1.8167496919631958,
|
| 126 |
+
"learning_rate": 3.9837865225468676e-05,
|
| 127 |
+
"loss": 0.288,
|
| 128 |
+
"step": 9316
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 14.431105613708496,
|
| 133 |
+
"learning_rate": 3.8912345887519e-05,
|
| 134 |
+
"loss": 0.3442,
|
| 135 |
+
"step": 9864
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 4.341527462005615,
|
| 140 |
+
"learning_rate": 3.798682654956933e-05,
|
| 141 |
+
"loss": 0.2964,
|
| 142 |
+
"step": 10412
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 0.9708638191223145,
|
| 147 |
+
"learning_rate": 3.706130721161966e-05,
|
| 148 |
+
"loss": 0.2836,
|
| 149 |
+
"step": 10960
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.9091862559565882,
|
| 154 |
+
"eval_auc": 0.9327717478336053,
|
| 155 |
+
"eval_f1": 0.9394671651544857,
|
| 156 |
+
"eval_loss": 0.26499995589256287,
|
| 157 |
+
"eval_precision": 0.9356703902158447,
|
| 158 |
+
"eval_recall": 0.9432948788378197,
|
| 159 |
+
"eval_runtime": 90.2174,
|
| 160 |
+
"eval_samples_per_second": 486.148,
|
| 161 |
+
"eval_steps_per_second": 15.197,
|
| 162 |
+
"step": 10965
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.05,
|
| 166 |
+
"grad_norm": 10.155410766601562,
|
| 167 |
+
"learning_rate": 3.613578787366999e-05,
|
| 168 |
+
"loss": 0.2915,
|
| 169 |
+
"step": 11508
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.1,
|
| 173 |
+
"grad_norm": 13.481185913085938,
|
| 174 |
+
"learning_rate": 3.521026853572032e-05,
|
| 175 |
+
"loss": 0.2706,
|
| 176 |
+
"step": 12056
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.15,
|
| 180 |
+
"grad_norm": 11.898757934570312,
|
| 181 |
+
"learning_rate": 3.428474919777065e-05,
|
| 182 |
+
"loss": 0.2577,
|
| 183 |
+
"step": 12604
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.2,
|
| 187 |
+
"grad_norm": 102.29252624511719,
|
| 188 |
+
"learning_rate": 3.336091876372234e-05,
|
| 189 |
+
"loss": 0.2867,
|
| 190 |
+
"step": 13152
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.25,
|
| 194 |
+
"grad_norm": 0.8772763609886169,
|
| 195 |
+
"learning_rate": 3.243539942577267e-05,
|
| 196 |
+
"loss": 0.2543,
|
| 197 |
+
"step": 13700
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.3,
|
| 201 |
+
"grad_norm": 3.079983711242676,
|
| 202 |
+
"learning_rate": 3.1509880087823005e-05,
|
| 203 |
+
"loss": 0.2747,
|
| 204 |
+
"step": 14248
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.35,
|
| 208 |
+
"grad_norm": 2.654982805252075,
|
| 209 |
+
"learning_rate": 3.058436074987334e-05,
|
| 210 |
+
"loss": 0.2637,
|
| 211 |
+
"step": 14796
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.4,
|
| 215 |
+
"grad_norm": 8.28964900970459,
|
| 216 |
+
"learning_rate": 2.9658841411923666e-05,
|
| 217 |
+
"loss": 0.2433,
|
| 218 |
+
"step": 15344
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.45,
|
| 222 |
+
"grad_norm": 0.606247067451477,
|
| 223 |
+
"learning_rate": 2.873669988177673e-05,
|
| 224 |
+
"loss": 0.2496,
|
| 225 |
+
"step": 15892
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.5,
|
| 229 |
+
"grad_norm": 4.818925857543945,
|
| 230 |
+
"learning_rate": 2.781118054382706e-05,
|
| 231 |
+
"loss": 0.2344,
|
| 232 |
+
"step": 16440
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.55,
|
| 236 |
+
"grad_norm": 9.206971168518066,
|
| 237 |
+
"learning_rate": 2.6885661205877388e-05,
|
| 238 |
+
"loss": 0.224,
|
| 239 |
+
"step": 16988
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.6,
|
| 243 |
+
"grad_norm": 1.9517682790756226,
|
| 244 |
+
"learning_rate": 2.5960141867927716e-05,
|
| 245 |
+
"loss": 0.2115,
|
| 246 |
+
"step": 17536
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.65,
|
| 250 |
+
"grad_norm": 10.609549522399902,
|
| 251 |
+
"learning_rate": 2.503462252997805e-05,
|
| 252 |
+
"loss": 0.2102,
|
| 253 |
+
"step": 18084
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.7,
|
| 257 |
+
"grad_norm": 20.039274215698242,
|
| 258 |
+
"learning_rate": 2.4109103192028377e-05,
|
| 259 |
+
"loss": 0.2027,
|
| 260 |
+
"step": 18632
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.75,
|
| 264 |
+
"grad_norm": 2.285228729248047,
|
| 265 |
+
"learning_rate": 2.3183583854078706e-05,
|
| 266 |
+
"loss": 0.1995,
|
| 267 |
+
"step": 19180
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.8,
|
| 271 |
+
"grad_norm": 9.45280647277832,
|
| 272 |
+
"learning_rate": 2.2258064516129034e-05,
|
| 273 |
+
"loss": 0.2076,
|
| 274 |
+
"step": 19728
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.85,
|
| 278 |
+
"grad_norm": 8.692055702209473,
|
| 279 |
+
"learning_rate": 2.1332545178179363e-05,
|
| 280 |
+
"loss": 0.2075,
|
| 281 |
+
"step": 20276
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.9,
|
| 285 |
+
"grad_norm": 8.51143741607666,
|
| 286 |
+
"learning_rate": 2.040871474413106e-05,
|
| 287 |
+
"loss": 0.2097,
|
| 288 |
+
"step": 20824
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.95,
|
| 292 |
+
"grad_norm": 4.226066589355469,
|
| 293 |
+
"learning_rate": 1.948319540618139e-05,
|
| 294 |
+
"loss": 0.2153,
|
| 295 |
+
"step": 21372
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.0,
|
| 299 |
+
"grad_norm": 3.73645281791687,
|
| 300 |
+
"learning_rate": 1.855767606823172e-05,
|
| 301 |
+
"loss": 0.2082,
|
| 302 |
+
"step": 21920
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 0.9314621856403474,
|
| 307 |
+
"eval_auc": 0.96886043230506,
|
| 308 |
+
"eval_f1": 0.953925385487876,
|
| 309 |
+
"eval_loss": 0.2151412069797516,
|
| 310 |
+
"eval_precision": 0.9581845054809706,
|
| 311 |
+
"eval_recall": 0.9497039614234267,
|
| 312 |
+
"eval_runtime": 90.5052,
|
| 313 |
+
"eval_samples_per_second": 484.602,
|
| 314 |
+
"eval_steps_per_second": 15.148,
|
| 315 |
+
"step": 21930
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.05,
|
| 319 |
+
"grad_norm": 2.4432873725891113,
|
| 320 |
+
"learning_rate": 1.763215673028205e-05,
|
| 321 |
+
"loss": 0.1786,
|
| 322 |
+
"step": 22468
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.1,
|
| 326 |
+
"grad_norm": 0.6836100816726685,
|
| 327 |
+
"learning_rate": 1.6708326296233746e-05,
|
| 328 |
+
"loss": 0.1842,
|
| 329 |
+
"step": 23016
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.15,
|
| 333 |
+
"grad_norm": 2.6022326946258545,
|
| 334 |
+
"learning_rate": 1.5784495862185442e-05,
|
| 335 |
+
"loss": 0.1801,
|
| 336 |
+
"step": 23564
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.2,
|
| 340 |
+
"grad_norm": 1.9158451557159424,
|
| 341 |
+
"learning_rate": 1.4858976524235771e-05,
|
| 342 |
+
"loss": 0.1731,
|
| 343 |
+
"step": 24112
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.25,
|
| 347 |
+
"grad_norm": 7.503026485443115,
|
| 348 |
+
"learning_rate": 1.39334571862861e-05,
|
| 349 |
+
"loss": 0.1726,
|
| 350 |
+
"step": 24660
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.3,
|
| 354 |
+
"grad_norm": 3.1770987510681152,
|
| 355 |
+
"learning_rate": 1.300793784833643e-05,
|
| 356 |
+
"loss": 0.1771,
|
| 357 |
+
"step": 25208
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.35,
|
| 361 |
+
"grad_norm": 4.539430141448975,
|
| 362 |
+
"learning_rate": 1.208241851038676e-05,
|
| 363 |
+
"loss": 0.1551,
|
| 364 |
+
"step": 25756
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.4,
|
| 368 |
+
"grad_norm": 1.772599458694458,
|
| 369 |
+
"learning_rate": 1.1156899172437089e-05,
|
| 370 |
+
"loss": 0.1735,
|
| 371 |
+
"step": 26304
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.45,
|
| 375 |
+
"grad_norm": 3.809593439102173,
|
| 376 |
+
"learning_rate": 1.023137983448742e-05,
|
| 377 |
+
"loss": 0.1683,
|
| 378 |
+
"step": 26852
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.5,
|
| 382 |
+
"grad_norm": 10.1038179397583,
|
| 383 |
+
"learning_rate": 9.307549400439116e-06,
|
| 384 |
+
"loss": 0.1617,
|
| 385 |
+
"step": 27400
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.55,
|
| 389 |
+
"grad_norm": 18.696857452392578,
|
| 390 |
+
"learning_rate": 8.382030062489445e-06,
|
| 391 |
+
"loss": 0.1589,
|
| 392 |
+
"step": 27948
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.6,
|
| 396 |
+
"grad_norm": 15.82597827911377,
|
| 397 |
+
"learning_rate": 7.4565107245397735e-06,
|
| 398 |
+
"loss": 0.1636,
|
| 399 |
+
"step": 28496
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.65,
|
| 403 |
+
"grad_norm": 1.0566959381103516,
|
| 404 |
+
"learning_rate": 6.530991386590103e-06,
|
| 405 |
+
"loss": 0.1553,
|
| 406 |
+
"step": 29044
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.7,
|
| 410 |
+
"grad_norm": 13.043928146362305,
|
| 411 |
+
"learning_rate": 5.6054720486404325e-06,
|
| 412 |
+
"loss": 0.1532,
|
| 413 |
+
"step": 29592
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.75,
|
| 417 |
+
"grad_norm": 19.499807357788086,
|
| 418 |
+
"learning_rate": 4.679952710690762e-06,
|
| 419 |
+
"loss": 0.1426,
|
| 420 |
+
"step": 30140
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.8,
|
| 424 |
+
"grad_norm": 24.73866081237793,
|
| 425 |
+
"learning_rate": 3.756122276642459e-06,
|
| 426 |
+
"loss": 0.1514,
|
| 427 |
+
"step": 30688
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.85,
|
| 431 |
+
"grad_norm": 6.256073474884033,
|
| 432 |
+
"learning_rate": 2.8306029386927886e-06,
|
| 433 |
+
"loss": 0.1554,
|
| 434 |
+
"step": 31236
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.9,
|
| 438 |
+
"grad_norm": 0.34589943289756775,
|
| 439 |
+
"learning_rate": 1.9050836007431179e-06,
|
| 440 |
+
"loss": 0.1459,
|
| 441 |
+
"step": 31784
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.95,
|
| 445 |
+
"grad_norm": 2.303668737411499,
|
| 446 |
+
"learning_rate": 9.795642627934472e-07,
|
| 447 |
+
"loss": 0.1584,
|
| 448 |
+
"step": 32332
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.0,
|
| 452 |
+
"grad_norm": 4.459900379180908,
|
| 453 |
+
"learning_rate": 5.404492484377639e-08,
|
| 454 |
+
"loss": 0.152,
|
| 455 |
+
"step": 32880
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.0,
|
| 459 |
+
"eval_accuracy": 0.945028386420119,
|
| 460 |
+
"eval_auc": 0.9812675754686511,
|
| 461 |
+
"eval_f1": 0.9633213150168105,
|
| 462 |
+
"eval_loss": 0.1894965022802353,
|
| 463 |
+
"eval_precision": 0.9603846270512937,
|
| 464 |
+
"eval_recall": 0.9662760178233535,
|
| 465 |
+
"eval_runtime": 90.4032,
|
| 466 |
+
"eval_samples_per_second": 485.149,
|
| 467 |
+
"eval_steps_per_second": 15.165,
|
| 468 |
+
"step": 32895
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 548,
|
| 472 |
+
"max_steps": 32895,
|
| 473 |
+
"num_input_tokens_seen": 0,
|
| 474 |
+
"num_train_epochs": 3,
|
| 475 |
+
"save_steps": 500,
|
| 476 |
+
"total_flos": 3.46191659978112e+16,
|
| 477 |
+
"train_batch_size": 16,
|
| 478 |
+
"trial_name": null,
|
| 479 |
+
"trial_params": null
|
| 480 |
+
}
|
checkpoint-32895/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f003cc9821b5418306dca505da3f110a29d95a2ba42f015b362147654a64df6c
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-irony",
|
| 3 |
+
"_num_labels": 2,
|
| 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": "objective",
|
| 17 |
+
"1": "subjective"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"objective": 0,
|
| 23 |
+
"subjective": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.38.2",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
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:b8f49a8ffc04c3b84a4598c60063878faf5b7e8095ad4c640b00fd111bb5e7e8
|
| 3 |
+
size 498612824
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 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": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 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": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f003cc9821b5418306dca505da3f110a29d95a2ba42f015b362147654a64df6c
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-8s6z2-1g2hg/autotrain-data",
|
| 3 |
+
"model": "cardiffnlp/twitter-roberta-base-irony",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 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": "autotrain-8s6z2-1g2hg",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"save_strategy": "epoch",
|
| 25 |
+
"push_to_hub": true,
|
| 26 |
+
"repo_id": "Re0x10/autotrain-8s6z2-1g2hg",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "Re0x10",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|