Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-151626/config.json +38 -0
- checkpoint-151626/model.safetensors +3 -0
- checkpoint-151626/optimizer.pt +3 -0
- checkpoint-151626/rng_state.pth +3 -0
- checkpoint-151626/scheduler.pt +3 -0
- checkpoint-151626/trainer_state.json +480 -0
- checkpoint-151626/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-x093p-hx5uj/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.5569086074829102
|
| 18 |
+
|
| 19 |
+
f1: 0.7228346456692913
|
| 20 |
+
|
| 21 |
+
precision: 0.7442879859396577
|
| 22 |
+
|
| 23 |
+
recall: 0.7025833975232565
|
| 24 |
+
|
| 25 |
+
auc: 0.7977332639137609
|
| 26 |
+
|
| 27 |
+
accuracy: 0.7301227703966048
|
checkpoint-151626/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": 0,
|
| 17 |
+
"1": 1
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"0": 0,
|
| 23 |
+
"1": 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": "4.39.0",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
checkpoint-151626/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96b396d001ae20c2a3cb85dfc27c26d272e7739645f04ddd42a06b9fb5b4a01c
|
| 3 |
+
size 498612824
|
checkpoint-151626/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:693f83cc6b7275e2cfc7464cadd70dfea66f9792792cd708703fd29b41a5dc0c
|
| 3 |
+
size 997345530
|
checkpoint-151626/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55857201af24613bea191cfd67f16051cbf7092c27bf0451d9e40f397ef1beb9
|
| 3 |
+
size 14244
|
checkpoint-151626/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02858e348dffe5b6a07c1494c74801c91b8d602dcb240f21efa114af8f4fbd53
|
| 3 |
+
size 1064
|
checkpoint-151626/trainer_state.json
ADDED
|
@@ -0,0 +1,480 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5569086074829102,
|
| 3 |
+
"best_model_checkpoint": "autotrain-x093p-hx5uj/checkpoint-151626",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 151626,
|
| 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": 13.528254508972168,
|
| 14 |
+
"learning_rate": 8.322891248433688e-06,
|
| 15 |
+
"loss": 0.6037,
|
| 16 |
+
"step": 2527
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 6.234881401062012,
|
| 21 |
+
"learning_rate": 1.6652377497856626e-05,
|
| 22 |
+
"loss": 0.5365,
|
| 23 |
+
"step": 5054
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 6.378116607666016,
|
| 28 |
+
"learning_rate": 2.497856624678494e-05,
|
| 29 |
+
"loss": 0.5253,
|
| 30 |
+
"step": 7581
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 5.055317401885986,
|
| 35 |
+
"learning_rate": 3.330475499571325e-05,
|
| 36 |
+
"loss": 0.5203,
|
| 37 |
+
"step": 10108
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 4.5121283531188965,
|
| 42 |
+
"learning_rate": 4.163753874563082e-05,
|
| 43 |
+
"loss": 0.5218,
|
| 44 |
+
"step": 12635
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 6.2932353019714355,
|
| 49 |
+
"learning_rate": 4.997032249554838e-05,
|
| 50 |
+
"loss": 0.529,
|
| 51 |
+
"step": 15162
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 7.188355445861816,
|
| 56 |
+
"learning_rate": 4.9077771996805e-05,
|
| 57 |
+
"loss": 0.5321,
|
| 58 |
+
"step": 17689
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 6.847433567047119,
|
| 63 |
+
"learning_rate": 4.815224639645912e-05,
|
| 64 |
+
"loss": 0.5422,
|
| 65 |
+
"step": 20216
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 2.578587293624878,
|
| 70 |
+
"learning_rate": 4.7227087195796665e-05,
|
| 71 |
+
"loss": 0.5483,
|
| 72 |
+
"step": 22743
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 4.216546058654785,
|
| 77 |
+
"learning_rate": 4.630192799513422e-05,
|
| 78 |
+
"loss": 0.5498,
|
| 79 |
+
"step": 25270
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 2.6127026081085205,
|
| 84 |
+
"learning_rate": 4.537640239478833e-05,
|
| 85 |
+
"loss": 0.5704,
|
| 86 |
+
"step": 27797
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 126.20368194580078,
|
| 91 |
+
"learning_rate": 4.445087679444245e-05,
|
| 92 |
+
"loss": 0.5738,
|
| 93 |
+
"step": 30324
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 0.9784852862358093,
|
| 98 |
+
"learning_rate": 4.352535119409657e-05,
|
| 99 |
+
"loss": 0.6768,
|
| 100 |
+
"step": 32851
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 0.437886506319046,
|
| 105 |
+
"learning_rate": 4.259945919406726e-05,
|
| 106 |
+
"loss": 0.6946,
|
| 107 |
+
"step": 35378
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 0.6273123621940613,
|
| 112 |
+
"learning_rate": 4.167356719403795e-05,
|
| 113 |
+
"loss": 0.6939,
|
| 114 |
+
"step": 37905
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 0.861335039138794,
|
| 119 |
+
"learning_rate": 4.0747675194008635e-05,
|
| 120 |
+
"loss": 0.6939,
|
| 121 |
+
"step": 40432
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 0.29443585872650146,
|
| 126 |
+
"learning_rate": 3.9821783193979326e-05,
|
| 127 |
+
"loss": 0.6936,
|
| 128 |
+
"step": 42959
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 0.46252480149269104,
|
| 133 |
+
"learning_rate": 3.889589119395001e-05,
|
| 134 |
+
"loss": 0.6938,
|
| 135 |
+
"step": 45486
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 0.6377570033073425,
|
| 140 |
+
"learning_rate": 3.79699991939207e-05,
|
| 141 |
+
"loss": 0.6937,
|
| 142 |
+
"step": 48013
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 1.2946058511734009,
|
| 147 |
+
"learning_rate": 3.7044107193891384e-05,
|
| 148 |
+
"loss": 0.6935,
|
| 149 |
+
"step": 50540
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.5008854109988821,
|
| 154 |
+
"eval_auc": 0.5029709685293048,
|
| 155 |
+
"eval_f1": 0.667453234375206,
|
| 156 |
+
"eval_loss": 0.6931009292602539,
|
| 157 |
+
"eval_precision": 0.5008854109988821,
|
| 158 |
+
"eval_recall": 1.0,
|
| 159 |
+
"eval_runtime": 398.9285,
|
| 160 |
+
"eval_samples_per_second": 506.772,
|
| 161 |
+
"eval_steps_per_second": 15.837,
|
| 162 |
+
"step": 50542
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.05,
|
| 166 |
+
"grad_norm": 0.45646148920059204,
|
| 167 |
+
"learning_rate": 3.61185815935455e-05,
|
| 168 |
+
"loss": 0.6935,
|
| 169 |
+
"step": 53067
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.1,
|
| 173 |
+
"grad_norm": 0.8132770657539368,
|
| 174 |
+
"learning_rate": 3.5193422392883054e-05,
|
| 175 |
+
"loss": 0.6935,
|
| 176 |
+
"step": 55594
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.15,
|
| 180 |
+
"grad_norm": 0.6158613562583923,
|
| 181 |
+
"learning_rate": 3.426789679253717e-05,
|
| 182 |
+
"loss": 0.6934,
|
| 183 |
+
"step": 58121
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.2,
|
| 187 |
+
"grad_norm": 0.38074907660484314,
|
| 188 |
+
"learning_rate": 3.334237119219129e-05,
|
| 189 |
+
"loss": 0.6934,
|
| 190 |
+
"step": 60648
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.25,
|
| 194 |
+
"grad_norm": 0.5249632596969604,
|
| 195 |
+
"learning_rate": 3.2416845591845414e-05,
|
| 196 |
+
"loss": 0.6934,
|
| 197 |
+
"step": 63175
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.3,
|
| 201 |
+
"grad_norm": 0.40391218662261963,
|
| 202 |
+
"learning_rate": 3.149205279086639e-05,
|
| 203 |
+
"loss": 0.6933,
|
| 204 |
+
"step": 65702
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.35,
|
| 208 |
+
"grad_norm": 0.73256516456604,
|
| 209 |
+
"learning_rate": 3.056652719052051e-05,
|
| 210 |
+
"loss": 0.6934,
|
| 211 |
+
"step": 68229
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.4,
|
| 215 |
+
"grad_norm": 0.6353848576545715,
|
| 216 |
+
"learning_rate": 2.9640635190491196e-05,
|
| 217 |
+
"loss": 0.6933,
|
| 218 |
+
"step": 70756
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.45,
|
| 222 |
+
"grad_norm": 0.6625229716300964,
|
| 223 |
+
"learning_rate": 2.8715109590145317e-05,
|
| 224 |
+
"loss": 0.6933,
|
| 225 |
+
"step": 73283
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.5,
|
| 229 |
+
"grad_norm": 0.9426682591438293,
|
| 230 |
+
"learning_rate": 2.7789583989799435e-05,
|
| 231 |
+
"loss": 0.6933,
|
| 232 |
+
"step": 75810
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.55,
|
| 236 |
+
"grad_norm": 0.4453619122505188,
|
| 237 |
+
"learning_rate": 2.6864424789136984e-05,
|
| 238 |
+
"loss": 0.6934,
|
| 239 |
+
"step": 78337
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.6,
|
| 243 |
+
"grad_norm": 0.5262486934661865,
|
| 244 |
+
"learning_rate": 2.5938899188791105e-05,
|
| 245 |
+
"loss": 0.6934,
|
| 246 |
+
"step": 80864
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.65,
|
| 250 |
+
"grad_norm": 0.3632877469062805,
|
| 251 |
+
"learning_rate": 2.5013373588445223e-05,
|
| 252 |
+
"loss": 0.6933,
|
| 253 |
+
"step": 83391
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.7,
|
| 257 |
+
"grad_norm": 0.7931771874427795,
|
| 258 |
+
"learning_rate": 2.408784798809934e-05,
|
| 259 |
+
"loss": 0.6934,
|
| 260 |
+
"step": 85918
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.75,
|
| 264 |
+
"grad_norm": 1.3530712127685547,
|
| 265 |
+
"learning_rate": 2.316305518712032e-05,
|
| 266 |
+
"loss": 0.6934,
|
| 267 |
+
"step": 88445
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.8,
|
| 271 |
+
"grad_norm": 0.38422197103500366,
|
| 272 |
+
"learning_rate": 2.2237163187091008e-05,
|
| 273 |
+
"loss": 0.6933,
|
| 274 |
+
"step": 90972
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.85,
|
| 278 |
+
"grad_norm": 1.2061989307403564,
|
| 279 |
+
"learning_rate": 2.1311637586745126e-05,
|
| 280 |
+
"loss": 0.6932,
|
| 281 |
+
"step": 93499
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.9,
|
| 285 |
+
"grad_norm": 0.4834197759628296,
|
| 286 |
+
"learning_rate": 2.0386478386082674e-05,
|
| 287 |
+
"loss": 0.6932,
|
| 288 |
+
"step": 96026
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.95,
|
| 292 |
+
"grad_norm": 0.735875129699707,
|
| 293 |
+
"learning_rate": 1.9460586386053365e-05,
|
| 294 |
+
"loss": 0.6932,
|
| 295 |
+
"step": 98553
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.0,
|
| 299 |
+
"grad_norm": 1.0206878185272217,
|
| 300 |
+
"learning_rate": 1.853506078570748e-05,
|
| 301 |
+
"loss": 0.6932,
|
| 302 |
+
"step": 101080
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 0.4991145890011179,
|
| 307 |
+
"eval_auc": 0.5,
|
| 308 |
+
"eval_f1": 0.0,
|
| 309 |
+
"eval_loss": 0.6933991312980652,
|
| 310 |
+
"eval_precision": 0.0,
|
| 311 |
+
"eval_recall": 0.0,
|
| 312 |
+
"eval_runtime": 396.4422,
|
| 313 |
+
"eval_samples_per_second": 509.951,
|
| 314 |
+
"eval_steps_per_second": 15.937,
|
| 315 |
+
"step": 101084
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.05,
|
| 319 |
+
"grad_norm": 0.8820214867591858,
|
| 320 |
+
"learning_rate": 1.76095351853616e-05,
|
| 321 |
+
"loss": 0.6931,
|
| 322 |
+
"step": 103607
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.1,
|
| 326 |
+
"grad_norm": 0.6403705477714539,
|
| 327 |
+
"learning_rate": 1.668437598469915e-05,
|
| 328 |
+
"loss": 0.6929,
|
| 329 |
+
"step": 106134
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.15,
|
| 333 |
+
"grad_norm": 1.0637304782867432,
|
| 334 |
+
"learning_rate": 1.5758850384353267e-05,
|
| 335 |
+
"loss": 0.6931,
|
| 336 |
+
"step": 108661
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.2,
|
| 340 |
+
"grad_norm": 0.7373464703559875,
|
| 341 |
+
"learning_rate": 1.4834790382741109e-05,
|
| 342 |
+
"loss": 0.6885,
|
| 343 |
+
"step": 111188
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.25,
|
| 347 |
+
"grad_norm": 0.4359135925769806,
|
| 348 |
+
"learning_rate": 1.3909631182078658e-05,
|
| 349 |
+
"loss": 0.6837,
|
| 350 |
+
"step": 113715
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.3,
|
| 354 |
+
"grad_norm": 0.6893612146377563,
|
| 355 |
+
"learning_rate": 1.2983739182049348e-05,
|
| 356 |
+
"loss": 0.6933,
|
| 357 |
+
"step": 116242
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.35,
|
| 361 |
+
"grad_norm": 0.7403135895729065,
|
| 362 |
+
"learning_rate": 1.2057847182020035e-05,
|
| 363 |
+
"loss": 0.6932,
|
| 364 |
+
"step": 118769
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.4,
|
| 368 |
+
"grad_norm": 0.7331185936927795,
|
| 369 |
+
"learning_rate": 1.1131955181990724e-05,
|
| 370 |
+
"loss": 0.6933,
|
| 371 |
+
"step": 121296
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.45,
|
| 375 |
+
"grad_norm": 0.367553174495697,
|
| 376 |
+
"learning_rate": 1.0206063181961411e-05,
|
| 377 |
+
"loss": 0.6932,
|
| 378 |
+
"step": 123823
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.5,
|
| 382 |
+
"grad_norm": 0.6151570081710815,
|
| 383 |
+
"learning_rate": 9.280537581615529e-06,
|
| 384 |
+
"loss": 0.6933,
|
| 385 |
+
"step": 126350
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.55,
|
| 389 |
+
"grad_norm": 0.41076934337615967,
|
| 390 |
+
"learning_rate": 8.355011981269648e-06,
|
| 391 |
+
"loss": 0.6932,
|
| 392 |
+
"step": 128877
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.6,
|
| 396 |
+
"grad_norm": 0.6966183185577393,
|
| 397 |
+
"learning_rate": 7.429486380923767e-06,
|
| 398 |
+
"loss": 0.693,
|
| 399 |
+
"step": 131404
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.65,
|
| 403 |
+
"grad_norm": 0.7166994214057922,
|
| 404 |
+
"learning_rate": 6.504327180261316e-06,
|
| 405 |
+
"loss": 0.693,
|
| 406 |
+
"step": 133931
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.7,
|
| 410 |
+
"grad_norm": 0.5734882950782776,
|
| 411 |
+
"learning_rate": 5.578435180232004e-06,
|
| 412 |
+
"loss": 0.6932,
|
| 413 |
+
"step": 136458
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.75,
|
| 417 |
+
"grad_norm": 3.933840274810791,
|
| 418 |
+
"learning_rate": 4.654741578303277e-06,
|
| 419 |
+
"loss": 0.6589,
|
| 420 |
+
"step": 138985
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.8,
|
| 424 |
+
"grad_norm": 3.881413221359253,
|
| 425 |
+
"learning_rate": 3.729582377640826e-06,
|
| 426 |
+
"loss": 0.5948,
|
| 427 |
+
"step": 141512
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.85,
|
| 431 |
+
"grad_norm": 6.612663269042969,
|
| 432 |
+
"learning_rate": 2.804423176978375e-06,
|
| 433 |
+
"loss": 0.5777,
|
| 434 |
+
"step": 144039
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.9,
|
| 438 |
+
"grad_norm": 3.72625732421875,
|
| 439 |
+
"learning_rate": 1.878531176949063e-06,
|
| 440 |
+
"loss": 0.5599,
|
| 441 |
+
"step": 146566
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.95,
|
| 445 |
+
"grad_norm": 13.995951652526855,
|
| 446 |
+
"learning_rate": 9.530055766031819e-07,
|
| 447 |
+
"loss": 0.5495,
|
| 448 |
+
"step": 149093
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.0,
|
| 452 |
+
"grad_norm": 135.5903778076172,
|
| 453 |
+
"learning_rate": 2.7113576573869842e-08,
|
| 454 |
+
"loss": 0.5462,
|
| 455 |
+
"step": 151620
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.0,
|
| 459 |
+
"eval_accuracy": 0.7301227703966048,
|
| 460 |
+
"eval_auc": 0.7977332639137609,
|
| 461 |
+
"eval_f1": 0.7228346456692913,
|
| 462 |
+
"eval_loss": 0.5569086074829102,
|
| 463 |
+
"eval_precision": 0.7442879859396577,
|
| 464 |
+
"eval_recall": 0.7025833975232565,
|
| 465 |
+
"eval_runtime": 397.2212,
|
| 466 |
+
"eval_samples_per_second": 508.951,
|
| 467 |
+
"eval_steps_per_second": 15.905,
|
| 468 |
+
"step": 151626
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 2527,
|
| 472 |
+
"max_steps": 151626,
|
| 473 |
+
"num_input_tokens_seen": 0,
|
| 474 |
+
"num_train_epochs": 3,
|
| 475 |
+
"save_steps": 500,
|
| 476 |
+
"total_flos": 1.595755395205632e+17,
|
| 477 |
+
"train_batch_size": 16,
|
| 478 |
+
"trial_name": null,
|
| 479 |
+
"trial_params": null
|
| 480 |
+
}
|
checkpoint-151626/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aec014d239217e8b80dbc4cf665fc2594d12a51980e4cc82a3409a15e5f5182b
|
| 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": 0,
|
| 17 |
+
"1": 1
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"0": 0,
|
| 23 |
+
"1": 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": "4.39.0",
|
| 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 sha256:96b396d001ae20c2a3cb85dfc27c26d272e7739645f04ddd42a06b9fb5b4a01c
|
| 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:aec014d239217e8b80dbc4cf665fc2594d12a51980e4cc82a3409a15e5f5182b
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-x093p-hx5uj/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-x093p-hx5uj",
|
| 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-x093p-hx5uj",
|
| 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
|
|
|