Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-66/config.json +40 -0
- checkpoint-66/model.safetensors +3 -0
- checkpoint-66/optimizer.pt +3 -0
- checkpoint-66/rng_state.pth +3 -0
- checkpoint-66/scheduler.pt +3 -0
- checkpoint-66/trainer_state.json +558 -0
- checkpoint-66/training_args.bin +3 -0
- config.json +40 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Nov22_15-18-12_r-zkava01-hi-vgc5krt0-5228c-irak0/events.out.tfevents.1732288695.r-zkava01-hi-vgc5krt0-5228c-irak0.138.0 +2 -2
- runs/Nov22_15-18-12_r-zkava01-hi-vgc5krt0-5228c-irak0/events.out.tfevents.1732289139.r-zkava01-hi-vgc5krt0-5228c-irak0.138.1 +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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
|
| 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: 0.29650357365608215
|
| 17 |
+
|
| 18 |
+
f1_macro: 0.9078720022116249
|
| 19 |
+
|
| 20 |
+
f1_micro: 0.9302325581395349
|
| 21 |
+
|
| 22 |
+
f1_weighted: 0.9292296119852065
|
| 23 |
+
|
| 24 |
+
precision_macro: 0.949667616334283
|
| 25 |
+
|
| 26 |
+
precision_micro: 0.9302325581395349
|
| 27 |
+
|
| 28 |
+
precision_weighted: 0.9319552110249785
|
| 29 |
+
|
| 30 |
+
recall_macro: 0.8782051282051282
|
| 31 |
+
|
| 32 |
+
recall_micro: 0.9302325581395349
|
| 33 |
+
|
| 34 |
+
recall_weighted: 0.9302325581395349
|
| 35 |
+
|
| 36 |
+
accuracy: 0.9302325581395349
|
checkpoint-66/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
|
| 3 |
+
"_num_labels": 3,
|
| 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 |
+
"2": "2"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"0": 0,
|
| 24 |
+
"1": 1,
|
| 25 |
+
"2": 2
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 514,
|
| 29 |
+
"model_type": "roberta",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 1,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.46.2",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
checkpoint-66/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc86b831710ab503f425503d67aef1ed580fe34bc3f00edf30e8d45f6aafe0eb
|
| 3 |
+
size 498615900
|
checkpoint-66/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99e8aa02eddc868c7129e3743743597a0a217b5090f2633f86e552de44302030
|
| 3 |
+
size 997346042
|
checkpoint-66/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a54a4761840706aed25e7c76e8f5aefc2a4a1080dff286d9817786770e98ee9
|
| 3 |
+
size 13990
|
checkpoint-66/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc0ec60d8c290dfd16f33e6e6eb692c15927f6457b46119a2e5421dc3a097e68
|
| 3 |
+
size 1064
|
checkpoint-66/trainer_state.json
ADDED
|
@@ -0,0 +1,558 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.29650357365608215,
|
| 3 |
+
"best_model_checkpoint": "autotrain-revmo-53leq/checkpoint-66",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 66,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.045454545454545456,
|
| 13 |
+
"grad_norm": 28.6497802734375,
|
| 14 |
+
"learning_rate": 7.142857142857143e-06,
|
| 15 |
+
"loss": 0.4602,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09090909090909091,
|
| 20 |
+
"grad_norm": 12.750972747802734,
|
| 21 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 22 |
+
"loss": 0.4166,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13636363636363635,
|
| 27 |
+
"grad_norm": 16.603534698486328,
|
| 28 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 29 |
+
"loss": 0.5021,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18181818181818182,
|
| 34 |
+
"grad_norm": 17.277828216552734,
|
| 35 |
+
"learning_rate": 2.857142857142857e-05,
|
| 36 |
+
"loss": 0.4096,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22727272727272727,
|
| 41 |
+
"grad_norm": 11.877945899963379,
|
| 42 |
+
"learning_rate": 3.571428571428572e-05,
|
| 43 |
+
"loss": 0.2947,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2727272727272727,
|
| 48 |
+
"grad_norm": 11.792537689208984,
|
| 49 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 50 |
+
"loss": 0.2097,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3181818181818182,
|
| 55 |
+
"grad_norm": 46.741493225097656,
|
| 56 |
+
"learning_rate": 5e-05,
|
| 57 |
+
"loss": 1.1688,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.36363636363636365,
|
| 62 |
+
"grad_norm": 18.050052642822266,
|
| 63 |
+
"learning_rate": 4.915254237288136e-05,
|
| 64 |
+
"loss": 0.2662,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4090909090909091,
|
| 69 |
+
"grad_norm": 44.04240036010742,
|
| 70 |
+
"learning_rate": 4.8305084745762714e-05,
|
| 71 |
+
"loss": 0.7818,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.45454545454545453,
|
| 76 |
+
"grad_norm": 64.99262237548828,
|
| 77 |
+
"learning_rate": 4.745762711864407e-05,
|
| 78 |
+
"loss": 1.3822,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5,
|
| 83 |
+
"grad_norm": 15.207534790039062,
|
| 84 |
+
"learning_rate": 4.6610169491525425e-05,
|
| 85 |
+
"loss": 0.1982,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5454545454545454,
|
| 90 |
+
"grad_norm": 79.90739440917969,
|
| 91 |
+
"learning_rate": 4.5762711864406784e-05,
|
| 92 |
+
"loss": 0.4197,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5909090909090909,
|
| 97 |
+
"grad_norm": 56.48210906982422,
|
| 98 |
+
"learning_rate": 4.491525423728814e-05,
|
| 99 |
+
"loss": 1.0359,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6363636363636364,
|
| 104 |
+
"grad_norm": 56.141273498535156,
|
| 105 |
+
"learning_rate": 4.4067796610169495e-05,
|
| 106 |
+
"loss": 0.5439,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6818181818181818,
|
| 111 |
+
"grad_norm": 11.973394393920898,
|
| 112 |
+
"learning_rate": 4.3220338983050854e-05,
|
| 113 |
+
"loss": 0.1168,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7272727272727273,
|
| 118 |
+
"grad_norm": 42.663795471191406,
|
| 119 |
+
"learning_rate": 4.2372881355932206e-05,
|
| 120 |
+
"loss": 0.7024,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7727272727272727,
|
| 125 |
+
"grad_norm": 33.43160629272461,
|
| 126 |
+
"learning_rate": 4.152542372881356e-05,
|
| 127 |
+
"loss": 0.5774,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8181818181818182,
|
| 132 |
+
"grad_norm": 19.131776809692383,
|
| 133 |
+
"learning_rate": 4.067796610169492e-05,
|
| 134 |
+
"loss": 0.2992,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8636363636363636,
|
| 139 |
+
"grad_norm": 29.990232467651367,
|
| 140 |
+
"learning_rate": 3.983050847457627e-05,
|
| 141 |
+
"loss": 0.3489,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9090909090909091,
|
| 146 |
+
"grad_norm": 27.957719802856445,
|
| 147 |
+
"learning_rate": 3.898305084745763e-05,
|
| 148 |
+
"loss": 0.2338,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9545454545454546,
|
| 153 |
+
"grad_norm": 31.963809967041016,
|
| 154 |
+
"learning_rate": 3.813559322033898e-05,
|
| 155 |
+
"loss": 0.3252,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0,
|
| 160 |
+
"grad_norm": 38.80619812011719,
|
| 161 |
+
"learning_rate": 3.728813559322034e-05,
|
| 162 |
+
"loss": 0.2618,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.0,
|
| 167 |
+
"eval_accuracy": 0.7906976744186046,
|
| 168 |
+
"eval_f1_macro": 0.8060606060606061,
|
| 169 |
+
"eval_f1_micro": 0.7906976744186046,
|
| 170 |
+
"eval_f1_weighted": 0.79903352461492,
|
| 171 |
+
"eval_loss": 0.48887890577316284,
|
| 172 |
+
"eval_precision_macro": 0.8636363636363636,
|
| 173 |
+
"eval_precision_micro": 0.7906976744186046,
|
| 174 |
+
"eval_precision_weighted": 0.876321353065539,
|
| 175 |
+
"eval_recall_macro": 0.8141025641025642,
|
| 176 |
+
"eval_recall_micro": 0.7906976744186046,
|
| 177 |
+
"eval_recall_weighted": 0.7906976744186046,
|
| 178 |
+
"eval_runtime": 7.9869,
|
| 179 |
+
"eval_samples_per_second": 5.384,
|
| 180 |
+
"eval_steps_per_second": 0.376,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.0454545454545454,
|
| 185 |
+
"grad_norm": 3.3973186016082764,
|
| 186 |
+
"learning_rate": 3.644067796610169e-05,
|
| 187 |
+
"loss": 0.0647,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.0909090909090908,
|
| 192 |
+
"grad_norm": 28.498188018798828,
|
| 193 |
+
"learning_rate": 3.559322033898305e-05,
|
| 194 |
+
"loss": 0.3141,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1363636363636362,
|
| 199 |
+
"grad_norm": 6.814549922943115,
|
| 200 |
+
"learning_rate": 3.474576271186441e-05,
|
| 201 |
+
"loss": 0.0961,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.1818181818181819,
|
| 206 |
+
"grad_norm": 16.97162437438965,
|
| 207 |
+
"learning_rate": 3.389830508474576e-05,
|
| 208 |
+
"loss": 0.3739,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.2272727272727273,
|
| 213 |
+
"grad_norm": 22.352941513061523,
|
| 214 |
+
"learning_rate": 3.305084745762712e-05,
|
| 215 |
+
"loss": 0.1515,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.2727272727272727,
|
| 220 |
+
"grad_norm": 77.6449966430664,
|
| 221 |
+
"learning_rate": 3.2203389830508473e-05,
|
| 222 |
+
"loss": 0.2559,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.3181818181818181,
|
| 227 |
+
"grad_norm": 5.475510597229004,
|
| 228 |
+
"learning_rate": 3.135593220338983e-05,
|
| 229 |
+
"loss": 0.0531,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3636363636363638,
|
| 234 |
+
"grad_norm": 44.47045135498047,
|
| 235 |
+
"learning_rate": 3.050847457627119e-05,
|
| 236 |
+
"loss": 0.2621,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.4090909090909092,
|
| 241 |
+
"grad_norm": 44.55425262451172,
|
| 242 |
+
"learning_rate": 2.9661016949152544e-05,
|
| 243 |
+
"loss": 0.3704,
|
| 244 |
+
"step": 31
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.4545454545454546,
|
| 248 |
+
"grad_norm": 19.289321899414062,
|
| 249 |
+
"learning_rate": 2.88135593220339e-05,
|
| 250 |
+
"loss": 0.0849,
|
| 251 |
+
"step": 32
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.5,
|
| 255 |
+
"grad_norm": 41.094688415527344,
|
| 256 |
+
"learning_rate": 2.7966101694915255e-05,
|
| 257 |
+
"loss": 0.4387,
|
| 258 |
+
"step": 33
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.5454545454545454,
|
| 262 |
+
"grad_norm": 21.01316261291504,
|
| 263 |
+
"learning_rate": 2.711864406779661e-05,
|
| 264 |
+
"loss": 0.1633,
|
| 265 |
+
"step": 34
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.5909090909090908,
|
| 269 |
+
"grad_norm": 38.75764465332031,
|
| 270 |
+
"learning_rate": 2.627118644067797e-05,
|
| 271 |
+
"loss": 0.2388,
|
| 272 |
+
"step": 35
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.6363636363636362,
|
| 276 |
+
"grad_norm": 4.39246129989624,
|
| 277 |
+
"learning_rate": 2.5423728813559322e-05,
|
| 278 |
+
"loss": 0.0239,
|
| 279 |
+
"step": 36
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.6818181818181817,
|
| 283 |
+
"grad_norm": 3.055365562438965,
|
| 284 |
+
"learning_rate": 2.457627118644068e-05,
|
| 285 |
+
"loss": 0.0268,
|
| 286 |
+
"step": 37
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.7272727272727273,
|
| 290 |
+
"grad_norm": 13.96273422241211,
|
| 291 |
+
"learning_rate": 2.3728813559322036e-05,
|
| 292 |
+
"loss": 0.0578,
|
| 293 |
+
"step": 38
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.7727272727272727,
|
| 297 |
+
"grad_norm": 2.8645408153533936,
|
| 298 |
+
"learning_rate": 2.2881355932203392e-05,
|
| 299 |
+
"loss": 0.0209,
|
| 300 |
+
"step": 39
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.8181818181818183,
|
| 304 |
+
"grad_norm": 1.836397647857666,
|
| 305 |
+
"learning_rate": 2.2033898305084748e-05,
|
| 306 |
+
"loss": 0.0236,
|
| 307 |
+
"step": 40
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.8636363636363638,
|
| 311 |
+
"grad_norm": 0.4018004834651947,
|
| 312 |
+
"learning_rate": 2.1186440677966103e-05,
|
| 313 |
+
"loss": 0.0107,
|
| 314 |
+
"step": 41
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.9090909090909092,
|
| 318 |
+
"grad_norm": 4.601925373077393,
|
| 319 |
+
"learning_rate": 2.033898305084746e-05,
|
| 320 |
+
"loss": 0.03,
|
| 321 |
+
"step": 42
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.9545454545454546,
|
| 325 |
+
"grad_norm": 48.49919128417969,
|
| 326 |
+
"learning_rate": 1.9491525423728814e-05,
|
| 327 |
+
"loss": 1.0566,
|
| 328 |
+
"step": 43
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.0,
|
| 332 |
+
"grad_norm": 0.6449614763259888,
|
| 333 |
+
"learning_rate": 1.864406779661017e-05,
|
| 334 |
+
"loss": 0.0057,
|
| 335 |
+
"step": 44
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.0,
|
| 339 |
+
"eval_accuracy": 0.813953488372093,
|
| 340 |
+
"eval_f1_macro": 0.6898809523809524,
|
| 341 |
+
"eval_f1_micro": 0.813953488372093,
|
| 342 |
+
"eval_f1_weighted": 0.8011212624584718,
|
| 343 |
+
"eval_loss": 0.6852538585662842,
|
| 344 |
+
"eval_precision_macro": 0.8657513348588863,
|
| 345 |
+
"eval_precision_micro": 0.813953488372093,
|
| 346 |
+
"eval_precision_weighted": 0.85195040178809,
|
| 347 |
+
"eval_recall_macro": 0.6858974358974358,
|
| 348 |
+
"eval_recall_micro": 0.813953488372093,
|
| 349 |
+
"eval_recall_weighted": 0.813953488372093,
|
| 350 |
+
"eval_runtime": 8.2824,
|
| 351 |
+
"eval_samples_per_second": 5.192,
|
| 352 |
+
"eval_steps_per_second": 0.362,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.0454545454545454,
|
| 357 |
+
"grad_norm": 49.31159973144531,
|
| 358 |
+
"learning_rate": 1.7796610169491526e-05,
|
| 359 |
+
"loss": 0.4487,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.090909090909091,
|
| 364 |
+
"grad_norm": 5.494616985321045,
|
| 365 |
+
"learning_rate": 1.694915254237288e-05,
|
| 366 |
+
"loss": 0.0139,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.1363636363636362,
|
| 371 |
+
"grad_norm": 4.503355979919434,
|
| 372 |
+
"learning_rate": 1.6101694915254237e-05,
|
| 373 |
+
"loss": 0.0236,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.1818181818181817,
|
| 378 |
+
"grad_norm": 5.209221363067627,
|
| 379 |
+
"learning_rate": 1.5254237288135596e-05,
|
| 380 |
+
"loss": 0.0177,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.227272727272727,
|
| 385 |
+
"grad_norm": 7.11909818649292,
|
| 386 |
+
"learning_rate": 1.440677966101695e-05,
|
| 387 |
+
"loss": 0.7101,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.2727272727272725,
|
| 392 |
+
"grad_norm": 0.2786655128002167,
|
| 393 |
+
"learning_rate": 1.3559322033898305e-05,
|
| 394 |
+
"loss": 0.0055,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.3181818181818183,
|
| 399 |
+
"grad_norm": 1.114147663116455,
|
| 400 |
+
"learning_rate": 1.2711864406779661e-05,
|
| 401 |
+
"loss": 0.0099,
|
| 402 |
+
"step": 51
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.3636363636363638,
|
| 406 |
+
"grad_norm": 0.2622224688529968,
|
| 407 |
+
"learning_rate": 1.1864406779661018e-05,
|
| 408 |
+
"loss": 0.0077,
|
| 409 |
+
"step": 52
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.409090909090909,
|
| 413 |
+
"grad_norm": 26.776103973388672,
|
| 414 |
+
"learning_rate": 1.1016949152542374e-05,
|
| 415 |
+
"loss": 0.0448,
|
| 416 |
+
"step": 53
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.4545454545454546,
|
| 420 |
+
"grad_norm": 0.48683127760887146,
|
| 421 |
+
"learning_rate": 1.016949152542373e-05,
|
| 422 |
+
"loss": 0.008,
|
| 423 |
+
"step": 54
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.5,
|
| 427 |
+
"grad_norm": 0.2846999764442444,
|
| 428 |
+
"learning_rate": 9.322033898305085e-06,
|
| 429 |
+
"loss": 0.0068,
|
| 430 |
+
"step": 55
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.5454545454545454,
|
| 434 |
+
"grad_norm": 9.395466804504395,
|
| 435 |
+
"learning_rate": 8.47457627118644e-06,
|
| 436 |
+
"loss": 0.0232,
|
| 437 |
+
"step": 56
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.590909090909091,
|
| 441 |
+
"grad_norm": 0.19868876039981842,
|
| 442 |
+
"learning_rate": 7.627118644067798e-06,
|
| 443 |
+
"loss": 0.0045,
|
| 444 |
+
"step": 57
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.6363636363636362,
|
| 448 |
+
"grad_norm": 0.4353472590446472,
|
| 449 |
+
"learning_rate": 6.779661016949153e-06,
|
| 450 |
+
"loss": 0.0069,
|
| 451 |
+
"step": 58
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.6818181818181817,
|
| 455 |
+
"grad_norm": 1.6797751188278198,
|
| 456 |
+
"learning_rate": 5.932203389830509e-06,
|
| 457 |
+
"loss": 0.0121,
|
| 458 |
+
"step": 59
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.7272727272727275,
|
| 462 |
+
"grad_norm": 0.7504879832267761,
|
| 463 |
+
"learning_rate": 5.084745762711865e-06,
|
| 464 |
+
"loss": 0.0079,
|
| 465 |
+
"step": 60
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.7727272727272725,
|
| 469 |
+
"grad_norm": 0.19052772223949432,
|
| 470 |
+
"learning_rate": 4.23728813559322e-06,
|
| 471 |
+
"loss": 0.0059,
|
| 472 |
+
"step": 61
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.8181818181818183,
|
| 476 |
+
"grad_norm": 1.1264681816101074,
|
| 477 |
+
"learning_rate": 3.3898305084745763e-06,
|
| 478 |
+
"loss": 0.0078,
|
| 479 |
+
"step": 62
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.8636363636363638,
|
| 483 |
+
"grad_norm": 0.4816828668117523,
|
| 484 |
+
"learning_rate": 2.5423728813559323e-06,
|
| 485 |
+
"loss": 0.005,
|
| 486 |
+
"step": 63
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.909090909090909,
|
| 490 |
+
"grad_norm": 0.21697530150413513,
|
| 491 |
+
"learning_rate": 1.6949152542372882e-06,
|
| 492 |
+
"loss": 0.005,
|
| 493 |
+
"step": 64
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.9545454545454546,
|
| 497 |
+
"grad_norm": 11.91680908203125,
|
| 498 |
+
"learning_rate": 8.474576271186441e-07,
|
| 499 |
+
"loss": 0.0207,
|
| 500 |
+
"step": 65
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.0,
|
| 504 |
+
"grad_norm": 5.379342079162598,
|
| 505 |
+
"learning_rate": 0.0,
|
| 506 |
+
"loss": 0.0206,
|
| 507 |
+
"step": 66
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.0,
|
| 511 |
+
"eval_accuracy": 0.9302325581395349,
|
| 512 |
+
"eval_f1_macro": 0.9078720022116249,
|
| 513 |
+
"eval_f1_micro": 0.9302325581395349,
|
| 514 |
+
"eval_f1_weighted": 0.9292296119852065,
|
| 515 |
+
"eval_loss": 0.29650357365608215,
|
| 516 |
+
"eval_precision_macro": 0.949667616334283,
|
| 517 |
+
"eval_precision_micro": 0.9302325581395349,
|
| 518 |
+
"eval_precision_weighted": 0.9319552110249785,
|
| 519 |
+
"eval_recall_macro": 0.8782051282051282,
|
| 520 |
+
"eval_recall_micro": 0.9302325581395349,
|
| 521 |
+
"eval_recall_weighted": 0.9302325581395349,
|
| 522 |
+
"eval_runtime": 9.0133,
|
| 523 |
+
"eval_samples_per_second": 4.771,
|
| 524 |
+
"eval_steps_per_second": 0.333,
|
| 525 |
+
"step": 66
|
| 526 |
+
}
|
| 527 |
+
],
|
| 528 |
+
"logging_steps": 1,
|
| 529 |
+
"max_steps": 66,
|
| 530 |
+
"num_input_tokens_seen": 0,
|
| 531 |
+
"num_train_epochs": 3,
|
| 532 |
+
"save_steps": 500,
|
| 533 |
+
"stateful_callbacks": {
|
| 534 |
+
"EarlyStoppingCallback": {
|
| 535 |
+
"args": {
|
| 536 |
+
"early_stopping_patience": 5,
|
| 537 |
+
"early_stopping_threshold": 0.01
|
| 538 |
+
},
|
| 539 |
+
"attributes": {
|
| 540 |
+
"early_stopping_patience_counter": 0
|
| 541 |
+
}
|
| 542 |
+
},
|
| 543 |
+
"TrainerControl": {
|
| 544 |
+
"args": {
|
| 545 |
+
"should_epoch_stop": false,
|
| 546 |
+
"should_evaluate": false,
|
| 547 |
+
"should_log": false,
|
| 548 |
+
"should_save": true,
|
| 549 |
+
"should_training_stop": true
|
| 550 |
+
},
|
| 551 |
+
"attributes": {}
|
| 552 |
+
}
|
| 553 |
+
},
|
| 554 |
+
"total_flos": 33349625697024.0,
|
| 555 |
+
"train_batch_size": 8,
|
| 556 |
+
"trial_name": null,
|
| 557 |
+
"trial_params": null
|
| 558 |
+
}
|
checkpoint-66/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36b3f2ea06ad2c0acb62ef2145b7d485b08e4ed4cb5f6eb269d19c5d86925bd6
|
| 3 |
+
size 5304
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
|
| 3 |
+
"_num_labels": 3,
|
| 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 |
+
"2": "2"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"0": 0,
|
| 24 |
+
"1": 1,
|
| 25 |
+
"2": 2
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 514,
|
| 29 |
+
"model_type": "roberta",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 1,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.46.2",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
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:dc86b831710ab503f425503d67aef1ed580fe34bc3f00edf30e8d45f6aafe0eb
|
| 3 |
+
size 498615900
|
runs/Nov22_15-18-12_r-zkava01-hi-vgc5krt0-5228c-irak0/events.out.tfevents.1732288695.r-zkava01-hi-vgc5krt0-5228c-irak0.138.0
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 sha256:25b88f4d811c70d7432d2dad88320ef5a16a8bb2596eeefd8e817c872704bef7
|
| 3 |
+
size 21789
|
runs/Nov22_15-18-12_r-zkava01-hi-vgc5krt0-5228c-irak0/events.out.tfevents.1732289139.r-zkava01-hi-vgc5krt0-5228c-irak0.138.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e30131cf766cd608aa147b556db31e82032453d5fd50ea80ed85cb9fdb3f4fbb
|
| 3 |
+
size 906
|
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": false,
|
| 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 sha256:36b3f2ea06ad2c0acb62ef2145b7d485b08e4ed4cb5f6eb269d19c5d86925bd6
|
| 3 |
+
size 5304
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-revmo-53leq/autotrain-data",
|
| 3 |
+
"model": "cardiffnlp/twitter-roberta-base-sentiment-latest",
|
| 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-revmo-53leq",
|
| 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": "zkava01",
|
| 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
|
|
|