Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-300/config.json +34 -0
- checkpoint-300/model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/trainer_state.json +501 -0
- checkpoint-300/training_args.bin +3 -0
- config.json +34 -0
- model.safetensors +3 -0
- runs/Dec13_08-37-01_r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq/events.out.tfevents.1734079023.r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq.138.0 +2 -2
- runs/Dec13_08-37-01_r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq/events.out.tfevents.1734080788.r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq.138.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +72 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: sentence-transformers/all-mpnet-base-v2
|
| 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: 0.0028607482090592384
|
| 17 |
+
|
| 18 |
+
f1: 1.0
|
| 19 |
+
|
| 20 |
+
precision: 1.0
|
| 21 |
+
|
| 22 |
+
recall: 1.0
|
| 23 |
+
|
| 24 |
+
auc: 1.0
|
| 25 |
+
|
| 26 |
+
accuracy: 1.0
|
checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MPNetForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "0",
|
| 15 |
+
"1": "1"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "mpnet",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"relative_attention_num_buckets": 32,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.46.2",
|
| 33 |
+
"vocab_size": 30527
|
| 34 |
+
}
|
checkpoint-300/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b6c235898e3c18700ab62fa6d24b9ecb2c0a0bde809b47ee9a27cfdc4d37cb0
|
| 3 |
+
size 437975200
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b714491d03155c0ea12c41d2ad557f6f2aeeff2c1ae0be26eb7b118b868f21e
|
| 3 |
+
size 876066554
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ddf4eb02e917a839b50449a330c1d491ecea7d29591dae65c7c50e726939c49
|
| 3 |
+
size 13990
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cabdd96162ecddbb53d954d7eb1984d5ac789bd18a1ad68743eeb1f283f45df1
|
| 3 |
+
size 1064
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0028607482090592384,
|
| 3 |
+
"best_model_checkpoint": "autotrain-9ikup-ih7yd/checkpoint-300",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 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": 1.0231589078903198,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 0.6826,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 1.1381429433822632,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 0.6653,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 0.9357160925865173,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 0.6252,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 1.420783519744873,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 0.5543,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 1.1961886882781982,
|
| 42 |
+
"learning_rate": 4.166666666666667e-05,
|
| 43 |
+
"loss": 0.432,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 1.0095195770263672,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 0.3005,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 0.7485983967781067,
|
| 56 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 57 |
+
"loss": 0.185,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 0.5755214095115662,
|
| 63 |
+
"learning_rate": 4.814814814814815e-05,
|
| 64 |
+
"loss": 0.1152,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 0.4263462424278259,
|
| 70 |
+
"learning_rate": 4.722222222222222e-05,
|
| 71 |
+
"loss": 0.0794,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 0.3358534872531891,
|
| 77 |
+
"learning_rate": 4.62962962962963e-05,
|
| 78 |
+
"loss": 0.0557,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 0.2775576114654541,
|
| 84 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 85 |
+
"loss": 0.0434,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 0.23248009383678436,
|
| 91 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 92 |
+
"loss": 0.0336,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 0.2064099758863449,
|
| 98 |
+
"learning_rate": 4.351851851851852e-05,
|
| 99 |
+
"loss": 0.028,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 0.1811286062002182,
|
| 105 |
+
"learning_rate": 4.259259259259259e-05,
|
| 106 |
+
"loss": 0.0239,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 0.16121040284633636,
|
| 112 |
+
"learning_rate": 4.166666666666667e-05,
|
| 113 |
+
"loss": 0.0197,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 0.15021204948425293,
|
| 119 |
+
"learning_rate": 4.074074074074074e-05,
|
| 120 |
+
"loss": 0.0179,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 0.13360002636909485,
|
| 126 |
+
"learning_rate": 3.981481481481482e-05,
|
| 127 |
+
"loss": 0.0162,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 0.1236184760928154,
|
| 133 |
+
"learning_rate": 3.888888888888889e-05,
|
| 134 |
+
"loss": 0.0146,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 0.11776061356067657,
|
| 140 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 141 |
+
"loss": 0.0129,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 0.11281422525644302,
|
| 147 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 148 |
+
"loss": 0.012,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 1.0,
|
| 154 |
+
"eval_auc": 1.0,
|
| 155 |
+
"eval_f1": 1.0,
|
| 156 |
+
"eval_loss": 0.009027771651744843,
|
| 157 |
+
"eval_precision": 1.0,
|
| 158 |
+
"eval_recall": 1.0,
|
| 159 |
+
"eval_runtime": 36.0656,
|
| 160 |
+
"eval_samples_per_second": 5.545,
|
| 161 |
+
"eval_steps_per_second": 0.36,
|
| 162 |
+
"step": 100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.05,
|
| 166 |
+
"grad_norm": 0.09917238354682922,
|
| 167 |
+
"learning_rate": 3.611111111111111e-05,
|
| 168 |
+
"loss": 0.0112,
|
| 169 |
+
"step": 105
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.1,
|
| 173 |
+
"grad_norm": 0.1017189547419548,
|
| 174 |
+
"learning_rate": 3.518518518518519e-05,
|
| 175 |
+
"loss": 0.0106,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.15,
|
| 180 |
+
"grad_norm": 0.09118398278951645,
|
| 181 |
+
"learning_rate": 3.425925925925926e-05,
|
| 182 |
+
"loss": 0.0096,
|
| 183 |
+
"step": 115
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.2,
|
| 187 |
+
"grad_norm": 0.08792706578969955,
|
| 188 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 189 |
+
"loss": 0.0091,
|
| 190 |
+
"step": 120
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.25,
|
| 194 |
+
"grad_norm": 0.08533497899770737,
|
| 195 |
+
"learning_rate": 3.240740740740741e-05,
|
| 196 |
+
"loss": 0.0087,
|
| 197 |
+
"step": 125
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.3,
|
| 201 |
+
"grad_norm": 0.07599101215600967,
|
| 202 |
+
"learning_rate": 3.148148148148148e-05,
|
| 203 |
+
"loss": 0.0083,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.35,
|
| 208 |
+
"grad_norm": 0.07442031055688858,
|
| 209 |
+
"learning_rate": 3.055555555555556e-05,
|
| 210 |
+
"loss": 0.0075,
|
| 211 |
+
"step": 135
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.4,
|
| 215 |
+
"grad_norm": 0.07316122204065323,
|
| 216 |
+
"learning_rate": 2.962962962962963e-05,
|
| 217 |
+
"loss": 0.0076,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.45,
|
| 222 |
+
"grad_norm": 0.06952174752950668,
|
| 223 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 224 |
+
"loss": 0.0069,
|
| 225 |
+
"step": 145
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.5,
|
| 229 |
+
"grad_norm": 0.0664600282907486,
|
| 230 |
+
"learning_rate": 2.777777777777778e-05,
|
| 231 |
+
"loss": 0.0067,
|
| 232 |
+
"step": 150
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.55,
|
| 236 |
+
"grad_norm": 0.06737347692251205,
|
| 237 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 238 |
+
"loss": 0.0067,
|
| 239 |
+
"step": 155
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.6,
|
| 243 |
+
"grad_norm": 0.06326944380998611,
|
| 244 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 245 |
+
"loss": 0.0064,
|
| 246 |
+
"step": 160
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.65,
|
| 250 |
+
"grad_norm": 0.06255871057510376,
|
| 251 |
+
"learning_rate": 2.5e-05,
|
| 252 |
+
"loss": 0.0061,
|
| 253 |
+
"step": 165
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.7,
|
| 257 |
+
"grad_norm": 0.05803116410970688,
|
| 258 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 259 |
+
"loss": 0.0057,
|
| 260 |
+
"step": 170
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.75,
|
| 264 |
+
"grad_norm": 0.0586419552564621,
|
| 265 |
+
"learning_rate": 2.314814814814815e-05,
|
| 266 |
+
"loss": 0.0056,
|
| 267 |
+
"step": 175
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.8,
|
| 271 |
+
"grad_norm": 0.053392261266708374,
|
| 272 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 273 |
+
"loss": 0.0054,
|
| 274 |
+
"step": 180
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.85,
|
| 278 |
+
"grad_norm": 0.05675709992647171,
|
| 279 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 280 |
+
"loss": 0.0053,
|
| 281 |
+
"step": 185
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.9,
|
| 285 |
+
"grad_norm": 0.05368509143590927,
|
| 286 |
+
"learning_rate": 2.037037037037037e-05,
|
| 287 |
+
"loss": 0.0051,
|
| 288 |
+
"step": 190
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.95,
|
| 292 |
+
"grad_norm": 0.05122752860188484,
|
| 293 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 294 |
+
"loss": 0.0051,
|
| 295 |
+
"step": 195
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.0,
|
| 299 |
+
"grad_norm": 0.05085288733243942,
|
| 300 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 301 |
+
"loss": 0.0048,
|
| 302 |
+
"step": 200
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 1.0,
|
| 307 |
+
"eval_auc": 1.0,
|
| 308 |
+
"eval_f1": 1.0,
|
| 309 |
+
"eval_loss": 0.0036500704009085894,
|
| 310 |
+
"eval_precision": 1.0,
|
| 311 |
+
"eval_recall": 1.0,
|
| 312 |
+
"eval_runtime": 38.0889,
|
| 313 |
+
"eval_samples_per_second": 5.251,
|
| 314 |
+
"eval_steps_per_second": 0.341,
|
| 315 |
+
"step": 200
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.05,
|
| 319 |
+
"grad_norm": 0.05097561329603195,
|
| 320 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 321 |
+
"loss": 0.0047,
|
| 322 |
+
"step": 205
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.1,
|
| 326 |
+
"grad_norm": 0.04888813570141792,
|
| 327 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 328 |
+
"loss": 0.0046,
|
| 329 |
+
"step": 210
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.15,
|
| 333 |
+
"grad_norm": 0.04953450709581375,
|
| 334 |
+
"learning_rate": 1.574074074074074e-05,
|
| 335 |
+
"loss": 0.0047,
|
| 336 |
+
"step": 215
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.2,
|
| 340 |
+
"grad_norm": 0.05090043693780899,
|
| 341 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 342 |
+
"loss": 0.0047,
|
| 343 |
+
"step": 220
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.25,
|
| 347 |
+
"grad_norm": 0.04786603897809982,
|
| 348 |
+
"learning_rate": 1.388888888888889e-05,
|
| 349 |
+
"loss": 0.0044,
|
| 350 |
+
"step": 225
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.3,
|
| 354 |
+
"grad_norm": 0.046088654547929764,
|
| 355 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 356 |
+
"loss": 0.0042,
|
| 357 |
+
"step": 230
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.35,
|
| 361 |
+
"grad_norm": 0.04463566094636917,
|
| 362 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 363 |
+
"loss": 0.0041,
|
| 364 |
+
"step": 235
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.4,
|
| 368 |
+
"grad_norm": 0.04407651722431183,
|
| 369 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 370 |
+
"loss": 0.0041,
|
| 371 |
+
"step": 240
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.45,
|
| 375 |
+
"grad_norm": 0.04530609771609306,
|
| 376 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 377 |
+
"loss": 0.0043,
|
| 378 |
+
"step": 245
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.5,
|
| 382 |
+
"grad_norm": 0.0432138666510582,
|
| 383 |
+
"learning_rate": 9.259259259259259e-06,
|
| 384 |
+
"loss": 0.004,
|
| 385 |
+
"step": 250
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.55,
|
| 389 |
+
"grad_norm": 0.04460172727704048,
|
| 390 |
+
"learning_rate": 8.333333333333334e-06,
|
| 391 |
+
"loss": 0.0041,
|
| 392 |
+
"step": 255
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.6,
|
| 396 |
+
"grad_norm": 0.04314126819372177,
|
| 397 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 398 |
+
"loss": 0.0039,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.65,
|
| 403 |
+
"grad_norm": 0.04184052720665932,
|
| 404 |
+
"learning_rate": 6.481481481481481e-06,
|
| 405 |
+
"loss": 0.004,
|
| 406 |
+
"step": 265
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.7,
|
| 410 |
+
"grad_norm": 0.04184694215655327,
|
| 411 |
+
"learning_rate": 5.555555555555556e-06,
|
| 412 |
+
"loss": 0.0037,
|
| 413 |
+
"step": 270
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.75,
|
| 417 |
+
"grad_norm": 0.04550705850124359,
|
| 418 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 419 |
+
"loss": 0.0039,
|
| 420 |
+
"step": 275
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.8,
|
| 424 |
+
"grad_norm": 0.04213162884116173,
|
| 425 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 426 |
+
"loss": 0.0039,
|
| 427 |
+
"step": 280
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.85,
|
| 431 |
+
"grad_norm": 0.0391254797577858,
|
| 432 |
+
"learning_rate": 2.777777777777778e-06,
|
| 433 |
+
"loss": 0.0037,
|
| 434 |
+
"step": 285
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.9,
|
| 438 |
+
"grad_norm": 0.03980780765414238,
|
| 439 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 440 |
+
"loss": 0.0039,
|
| 441 |
+
"step": 290
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.95,
|
| 445 |
+
"grad_norm": 0.040770865976810455,
|
| 446 |
+
"learning_rate": 9.259259259259259e-07,
|
| 447 |
+
"loss": 0.0039,
|
| 448 |
+
"step": 295
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.0,
|
| 452 |
+
"grad_norm": 0.042418189346790314,
|
| 453 |
+
"learning_rate": 0.0,
|
| 454 |
+
"loss": 0.0038,
|
| 455 |
+
"step": 300
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.0,
|
| 459 |
+
"eval_accuracy": 1.0,
|
| 460 |
+
"eval_auc": 1.0,
|
| 461 |
+
"eval_f1": 1.0,
|
| 462 |
+
"eval_loss": 0.0028607482090592384,
|
| 463 |
+
"eval_precision": 1.0,
|
| 464 |
+
"eval_recall": 1.0,
|
| 465 |
+
"eval_runtime": 35.7094,
|
| 466 |
+
"eval_samples_per_second": 5.601,
|
| 467 |
+
"eval_steps_per_second": 0.364,
|
| 468 |
+
"step": 300
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 5,
|
| 472 |
+
"max_steps": 300,
|
| 473 |
+
"num_input_tokens_seen": 0,
|
| 474 |
+
"num_train_epochs": 3,
|
| 475 |
+
"save_steps": 500,
|
| 476 |
+
"stateful_callbacks": {
|
| 477 |
+
"EarlyStoppingCallback": {
|
| 478 |
+
"args": {
|
| 479 |
+
"early_stopping_patience": 5,
|
| 480 |
+
"early_stopping_threshold": 0.01
|
| 481 |
+
},
|
| 482 |
+
"attributes": {
|
| 483 |
+
"early_stopping_patience_counter": 2
|
| 484 |
+
}
|
| 485 |
+
},
|
| 486 |
+
"TrainerControl": {
|
| 487 |
+
"args": {
|
| 488 |
+
"should_epoch_stop": false,
|
| 489 |
+
"should_evaluate": false,
|
| 490 |
+
"should_log": false,
|
| 491 |
+
"should_save": true,
|
| 492 |
+
"should_training_stop": true
|
| 493 |
+
},
|
| 494 |
+
"attributes": {}
|
| 495 |
+
}
|
| 496 |
+
},
|
| 497 |
+
"total_flos": 157866633216000.0,
|
| 498 |
+
"train_batch_size": 8,
|
| 499 |
+
"trial_name": null,
|
| 500 |
+
"trial_params": null
|
| 501 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1692f8b102d6f6942151e22defe7da2f241e967677bb6a5081ccc06ee269c4
|
| 3 |
+
size 5304
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MPNetForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "0",
|
| 15 |
+
"1": "1"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "mpnet",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"relative_attention_num_buckets": 32,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.46.2",
|
| 33 |
+
"vocab_size": 30527
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b6c235898e3c18700ab62fa6d24b9ecb2c0a0bde809b47ee9a27cfdc4d37cb0
|
| 3 |
+
size 437975200
|
runs/Dec13_08-37-01_r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq/events.out.tfevents.1734079023.r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq.138.0
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:d6dfbfa07137f714470d4a7d542943e37b8dbfc1bfacb968045d91eff6e27f35
|
| 3 |
+
size 19610
|
runs/Dec13_08-37-01_r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq/events.out.tfevents.1734080788.r-milan97-autotrain-advanced-4wbl87oi-5e284-7f6qq.138.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a7b9cece79aab7661f56f28357ba33c547d533ec0bdcffb3485c8e3a5141d0
|
| 3 |
+
size 607
|
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 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30526": {
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "<s>",
|
| 55 |
+
"do_lower_case": true,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"mask_token": "<mask>",
|
| 58 |
+
"max_length": 128,
|
| 59 |
+
"model_max_length": 512,
|
| 60 |
+
"pad_to_multiple_of": null,
|
| 61 |
+
"pad_token": "<pad>",
|
| 62 |
+
"pad_token_type_id": 0,
|
| 63 |
+
"padding_side": "right",
|
| 64 |
+
"sep_token": "</s>",
|
| 65 |
+
"stride": 0,
|
| 66 |
+
"strip_accents": null,
|
| 67 |
+
"tokenize_chinese_chars": true,
|
| 68 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 69 |
+
"truncation_side": "right",
|
| 70 |
+
"truncation_strategy": "longest_first",
|
| 71 |
+
"unk_token": "[UNK]"
|
| 72 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1692f8b102d6f6942151e22defe7da2f241e967677bb6a5081ccc06ee269c4
|
| 3 |
+
size 5304
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-9ikup-ih7yd/autotrain-data",
|
| 3 |
+
"model": "sentence-transformers/all-mpnet-base-v2",
|
| 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": "autotrain-9ikup-ih7yd",
|
| 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": "Milan97",
|
| 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
|
|
|