Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-195/config.json +59 -0
- checkpoint-195/model.safetensors +3 -0
- checkpoint-195/optimizer.pt +3 -0
- checkpoint-195/rng_state.pth +3 -0
- checkpoint-195/scheduler.pt +3 -0
- checkpoint-195/trainer_state.json +551 -0
- checkpoint-195/training_args.bin +3 -0
- config.json +59 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jun19_22-00-52_r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh/events.out.tfevents.1718834454.r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh.329.0 +2 -2
- runs/Jun19_22-00-52_r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh/events.out.tfevents.1718835429.r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh.329.1 +3 -0
- special_tokens_map.json +15 -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: FacebookAI/roberta-base
|
| 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: 0.052504993975162506
|
| 17 |
+
|
| 18 |
+
f1_macro: 1.0
|
| 19 |
+
|
| 20 |
+
f1_micro: 1.0
|
| 21 |
+
|
| 22 |
+
f1_weighted: 1.0
|
| 23 |
+
|
| 24 |
+
precision_macro: 1.0
|
| 25 |
+
|
| 26 |
+
precision_micro: 1.0
|
| 27 |
+
|
| 28 |
+
precision_weighted: 1.0
|
| 29 |
+
|
| 30 |
+
recall_macro: 1.0
|
| 31 |
+
|
| 32 |
+
recall_micro: 1.0
|
| 33 |
+
|
| 34 |
+
recall_weighted: 1.0
|
| 35 |
+
|
| 36 |
+
accuracy: 1.0
|
checkpoint-195/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
+
"_num_labels": 13,
|
| 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 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "0",
|
| 16 |
+
"1": "1",
|
| 17 |
+
"2": "10",
|
| 18 |
+
"3": "11",
|
| 19 |
+
"4": "12",
|
| 20 |
+
"5": "2",
|
| 21 |
+
"6": "3",
|
| 22 |
+
"7": "4",
|
| 23 |
+
"8": "5",
|
| 24 |
+
"9": "6",
|
| 25 |
+
"10": "7",
|
| 26 |
+
"11": "8",
|
| 27 |
+
"12": "9"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"0": 0,
|
| 33 |
+
"1": 1,
|
| 34 |
+
"10": 2,
|
| 35 |
+
"11": 3,
|
| 36 |
+
"12": 4,
|
| 37 |
+
"2": 5,
|
| 38 |
+
"3": 6,
|
| 39 |
+
"4": 7,
|
| 40 |
+
"5": 8,
|
| 41 |
+
"6": 9,
|
| 42 |
+
"7": 10,
|
| 43 |
+
"8": 11,
|
| 44 |
+
"9": 12
|
| 45 |
+
},
|
| 46 |
+
"layer_norm_eps": 1e-05,
|
| 47 |
+
"max_position_embeddings": 514,
|
| 48 |
+
"model_type": "roberta",
|
| 49 |
+
"num_attention_heads": 12,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"problem_type": "single_label_classification",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.41.2",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
checkpoint-195/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:689d6073a6d72a9f9ed6c12c58c78d524bdc14a41e79574a6bdf30744306299f
|
| 3 |
+
size 498646660
|
checkpoint-195/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:462beeafdd95e640dd52e3a8bcab9d015ee5432460dd3b173b3581395404e887
|
| 3 |
+
size 997407482
|
checkpoint-195/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc2af80a02e5efd5229e3c1b21820119acb7ecbdf357647b97213598c1eabf65
|
| 3 |
+
size 13990
|
checkpoint-195/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0a5e699b011ecbc2fe39dbb0b7ae3e0ee510791eb6d67cdca486be5f6b29037
|
| 3 |
+
size 1064
|
checkpoint-195/trainer_state.json
ADDED
|
@@ -0,0 +1,551 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.052504993975162506,
|
| 3 |
+
"best_model_checkpoint": "RobertaArmControl/checkpoint-195",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 195,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.046153846153846156,
|
| 13 |
+
"grad_norm": 2.491260290145874,
|
| 14 |
+
"learning_rate": 7.5e-06,
|
| 15 |
+
"loss": 2.5616,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09230769230769231,
|
| 20 |
+
"grad_norm": 5.147457599639893,
|
| 21 |
+
"learning_rate": 1.5e-05,
|
| 22 |
+
"loss": 2.5421,
|
| 23 |
+
"step": 6
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13846153846153847,
|
| 27 |
+
"grad_norm": 3.6511762142181396,
|
| 28 |
+
"learning_rate": 2.25e-05,
|
| 29 |
+
"loss": 2.5744,
|
| 30 |
+
"step": 9
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18461538461538463,
|
| 34 |
+
"grad_norm": 2.999962091445923,
|
| 35 |
+
"learning_rate": 3e-05,
|
| 36 |
+
"loss": 2.5776,
|
| 37 |
+
"step": 12
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.23076923076923078,
|
| 41 |
+
"grad_norm": 28.02067756652832,
|
| 42 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 43 |
+
"loss": 2.5715,
|
| 44 |
+
"step": 15
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27692307692307694,
|
| 48 |
+
"grad_norm": 3.9126367568969727,
|
| 49 |
+
"learning_rate": 4.5e-05,
|
| 50 |
+
"loss": 2.5795,
|
| 51 |
+
"step": 18
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3230769230769231,
|
| 55 |
+
"grad_norm": 4.8196563720703125,
|
| 56 |
+
"learning_rate": 4.971428571428572e-05,
|
| 57 |
+
"loss": 2.5479,
|
| 58 |
+
"step": 21
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.36923076923076925,
|
| 62 |
+
"grad_norm": 3.9189937114715576,
|
| 63 |
+
"learning_rate": 4.885714285714286e-05,
|
| 64 |
+
"loss": 2.5692,
|
| 65 |
+
"step": 24
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4153846153846154,
|
| 69 |
+
"grad_norm": 5.880428791046143,
|
| 70 |
+
"learning_rate": 4.8e-05,
|
| 71 |
+
"loss": 2.5171,
|
| 72 |
+
"step": 27
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.46153846153846156,
|
| 76 |
+
"grad_norm": 6.521769046783447,
|
| 77 |
+
"learning_rate": 4.714285714285714e-05,
|
| 78 |
+
"loss": 2.4737,
|
| 79 |
+
"step": 30
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5076923076923077,
|
| 83 |
+
"grad_norm": 9.928788185119629,
|
| 84 |
+
"learning_rate": 4.628571428571429e-05,
|
| 85 |
+
"loss": 2.3593,
|
| 86 |
+
"step": 33
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5538461538461539,
|
| 90 |
+
"grad_norm": 12.504234313964844,
|
| 91 |
+
"learning_rate": 4.542857142857143e-05,
|
| 92 |
+
"loss": 2.1366,
|
| 93 |
+
"step": 36
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6,
|
| 97 |
+
"grad_norm": 9.821626663208008,
|
| 98 |
+
"learning_rate": 4.4571428571428574e-05,
|
| 99 |
+
"loss": 2.0206,
|
| 100 |
+
"step": 39
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6461538461538462,
|
| 104 |
+
"grad_norm": 13.857908248901367,
|
| 105 |
+
"learning_rate": 4.371428571428572e-05,
|
| 106 |
+
"loss": 1.9738,
|
| 107 |
+
"step": 42
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6923076923076923,
|
| 111 |
+
"grad_norm": 15.071351051330566,
|
| 112 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 113 |
+
"loss": 1.7894,
|
| 114 |
+
"step": 45
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7384615384615385,
|
| 118 |
+
"grad_norm": 9.994881629943848,
|
| 119 |
+
"learning_rate": 4.2e-05,
|
| 120 |
+
"loss": 1.5436,
|
| 121 |
+
"step": 48
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7846153846153846,
|
| 125 |
+
"grad_norm": 10.25603199005127,
|
| 126 |
+
"learning_rate": 4.1142857142857146e-05,
|
| 127 |
+
"loss": 1.5136,
|
| 128 |
+
"step": 51
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8307692307692308,
|
| 132 |
+
"grad_norm": 11.905317306518555,
|
| 133 |
+
"learning_rate": 4.028571428571429e-05,
|
| 134 |
+
"loss": 1.4274,
|
| 135 |
+
"step": 54
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8769230769230769,
|
| 139 |
+
"grad_norm": 10.349802017211914,
|
| 140 |
+
"learning_rate": 3.942857142857143e-05,
|
| 141 |
+
"loss": 1.263,
|
| 142 |
+
"step": 57
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9230769230769231,
|
| 146 |
+
"grad_norm": 9.09520149230957,
|
| 147 |
+
"learning_rate": 3.857142857142858e-05,
|
| 148 |
+
"loss": 1.2399,
|
| 149 |
+
"step": 60
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9692307692307692,
|
| 153 |
+
"grad_norm": 11.345512390136719,
|
| 154 |
+
"learning_rate": 3.771428571428572e-05,
|
| 155 |
+
"loss": 1.1636,
|
| 156 |
+
"step": 63
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0,
|
| 160 |
+
"eval_accuracy": 0.7538461538461538,
|
| 161 |
+
"eval_f1_macro": 0.6768845189897822,
|
| 162 |
+
"eval_f1_micro": 0.7538461538461538,
|
| 163 |
+
"eval_f1_weighted": 0.6768845189897823,
|
| 164 |
+
"eval_loss": 0.8756860494613647,
|
| 165 |
+
"eval_precision_macro": 0.6398601398601399,
|
| 166 |
+
"eval_precision_micro": 0.7538461538461538,
|
| 167 |
+
"eval_precision_weighted": 0.6398601398601399,
|
| 168 |
+
"eval_recall_macro": 0.7538461538461539,
|
| 169 |
+
"eval_recall_micro": 0.7538461538461538,
|
| 170 |
+
"eval_recall_weighted": 0.7538461538461538,
|
| 171 |
+
"eval_runtime": 19.5321,
|
| 172 |
+
"eval_samples_per_second": 6.656,
|
| 173 |
+
"eval_steps_per_second": 0.461,
|
| 174 |
+
"step": 65
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.0153846153846153,
|
| 178 |
+
"grad_norm": 9.532114028930664,
|
| 179 |
+
"learning_rate": 3.685714285714286e-05,
|
| 180 |
+
"loss": 1.1631,
|
| 181 |
+
"step": 66
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.0615384615384615,
|
| 185 |
+
"grad_norm": 7.3828606605529785,
|
| 186 |
+
"learning_rate": 3.6e-05,
|
| 187 |
+
"loss": 0.876,
|
| 188 |
+
"step": 69
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.1076923076923078,
|
| 192 |
+
"grad_norm": 7.816571235656738,
|
| 193 |
+
"learning_rate": 3.514285714285714e-05,
|
| 194 |
+
"loss": 0.8118,
|
| 195 |
+
"step": 72
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1538461538461537,
|
| 199 |
+
"grad_norm": 8.26477336883545,
|
| 200 |
+
"learning_rate": 3.428571428571429e-05,
|
| 201 |
+
"loss": 0.7934,
|
| 202 |
+
"step": 75
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.2,
|
| 206 |
+
"grad_norm": 7.570327281951904,
|
| 207 |
+
"learning_rate": 3.342857142857143e-05,
|
| 208 |
+
"loss": 0.8536,
|
| 209 |
+
"step": 78
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.2461538461538462,
|
| 213 |
+
"grad_norm": 6.143610954284668,
|
| 214 |
+
"learning_rate": 3.257142857142857e-05,
|
| 215 |
+
"loss": 0.7207,
|
| 216 |
+
"step": 81
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.2923076923076924,
|
| 220 |
+
"grad_norm": 6.489696025848389,
|
| 221 |
+
"learning_rate": 3.1714285714285715e-05,
|
| 222 |
+
"loss": 0.5507,
|
| 223 |
+
"step": 84
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.3384615384615386,
|
| 227 |
+
"grad_norm": 4.658430576324463,
|
| 228 |
+
"learning_rate": 3.0857142857142856e-05,
|
| 229 |
+
"loss": 0.5861,
|
| 230 |
+
"step": 87
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3846153846153846,
|
| 234 |
+
"grad_norm": 5.084001064300537,
|
| 235 |
+
"learning_rate": 3e-05,
|
| 236 |
+
"loss": 0.5498,
|
| 237 |
+
"step": 90
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.4307692307692308,
|
| 241 |
+
"grad_norm": 4.474237442016602,
|
| 242 |
+
"learning_rate": 2.9142857142857146e-05,
|
| 243 |
+
"loss": 0.4172,
|
| 244 |
+
"step": 93
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.476923076923077,
|
| 248 |
+
"grad_norm": 3.8236639499664307,
|
| 249 |
+
"learning_rate": 2.8285714285714287e-05,
|
| 250 |
+
"loss": 0.5276,
|
| 251 |
+
"step": 96
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.523076923076923,
|
| 255 |
+
"grad_norm": 3.525235891342163,
|
| 256 |
+
"learning_rate": 2.742857142857143e-05,
|
| 257 |
+
"loss": 0.4986,
|
| 258 |
+
"step": 99
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.5692307692307692,
|
| 262 |
+
"grad_norm": 5.637748718261719,
|
| 263 |
+
"learning_rate": 2.6571428571428576e-05,
|
| 264 |
+
"loss": 0.3992,
|
| 265 |
+
"step": 102
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.6153846153846154,
|
| 269 |
+
"grad_norm": 6.278521537780762,
|
| 270 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 271 |
+
"loss": 0.5631,
|
| 272 |
+
"step": 105
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.6615384615384614,
|
| 276 |
+
"grad_norm": 5.949018478393555,
|
| 277 |
+
"learning_rate": 2.485714285714286e-05,
|
| 278 |
+
"loss": 0.5122,
|
| 279 |
+
"step": 108
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.7076923076923078,
|
| 283 |
+
"grad_norm": 6.435329914093018,
|
| 284 |
+
"learning_rate": 2.4e-05,
|
| 285 |
+
"loss": 0.4512,
|
| 286 |
+
"step": 111
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.7538461538461538,
|
| 290 |
+
"grad_norm": 5.9377522468566895,
|
| 291 |
+
"learning_rate": 2.3142857142857145e-05,
|
| 292 |
+
"loss": 0.463,
|
| 293 |
+
"step": 114
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.8,
|
| 297 |
+
"grad_norm": 4.556524753570557,
|
| 298 |
+
"learning_rate": 2.2285714285714287e-05,
|
| 299 |
+
"loss": 0.3825,
|
| 300 |
+
"step": 117
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.8461538461538463,
|
| 304 |
+
"grad_norm": 4.213245391845703,
|
| 305 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 306 |
+
"loss": 0.4115,
|
| 307 |
+
"step": 120
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.8923076923076922,
|
| 311 |
+
"grad_norm": 7.243228912353516,
|
| 312 |
+
"learning_rate": 2.0571428571428573e-05,
|
| 313 |
+
"loss": 0.4403,
|
| 314 |
+
"step": 123
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.9384615384615385,
|
| 318 |
+
"grad_norm": 6.15199613571167,
|
| 319 |
+
"learning_rate": 1.9714285714285714e-05,
|
| 320 |
+
"loss": 0.3645,
|
| 321 |
+
"step": 126
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.9846153846153847,
|
| 325 |
+
"grad_norm": 4.317075252532959,
|
| 326 |
+
"learning_rate": 1.885714285714286e-05,
|
| 327 |
+
"loss": 0.3226,
|
| 328 |
+
"step": 129
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.0,
|
| 332 |
+
"eval_accuracy": 0.9769230769230769,
|
| 333 |
+
"eval_f1_macro": 0.9763918945504624,
|
| 334 |
+
"eval_f1_micro": 0.9769230769230769,
|
| 335 |
+
"eval_f1_weighted": 0.9763918945504624,
|
| 336 |
+
"eval_loss": 0.2216302901506424,
|
| 337 |
+
"eval_precision_macro": 0.9822485207100592,
|
| 338 |
+
"eval_precision_micro": 0.9769230769230769,
|
| 339 |
+
"eval_precision_weighted": 0.9822485207100592,
|
| 340 |
+
"eval_recall_macro": 0.9769230769230769,
|
| 341 |
+
"eval_recall_micro": 0.9769230769230769,
|
| 342 |
+
"eval_recall_weighted": 0.9769230769230769,
|
| 343 |
+
"eval_runtime": 19.6757,
|
| 344 |
+
"eval_samples_per_second": 6.607,
|
| 345 |
+
"eval_steps_per_second": 0.457,
|
| 346 |
+
"step": 130
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.0307692307692307,
|
| 350 |
+
"grad_norm": 2.3677194118499756,
|
| 351 |
+
"learning_rate": 1.8e-05,
|
| 352 |
+
"loss": 0.2562,
|
| 353 |
+
"step": 132
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.076923076923077,
|
| 357 |
+
"grad_norm": 3.6434857845306396,
|
| 358 |
+
"learning_rate": 1.7142857142857145e-05,
|
| 359 |
+
"loss": 0.2645,
|
| 360 |
+
"step": 135
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.123076923076923,
|
| 364 |
+
"grad_norm": 5.34273099899292,
|
| 365 |
+
"learning_rate": 1.6285714285714287e-05,
|
| 366 |
+
"loss": 0.2593,
|
| 367 |
+
"step": 138
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.169230769230769,
|
| 371 |
+
"grad_norm": 5.076902866363525,
|
| 372 |
+
"learning_rate": 1.5428571428571428e-05,
|
| 373 |
+
"loss": 0.2734,
|
| 374 |
+
"step": 141
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.2153846153846155,
|
| 378 |
+
"grad_norm": 3.1268246173858643,
|
| 379 |
+
"learning_rate": 1.4571428571428573e-05,
|
| 380 |
+
"loss": 0.1391,
|
| 381 |
+
"step": 144
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.2615384615384615,
|
| 385 |
+
"grad_norm": 6.289782524108887,
|
| 386 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 387 |
+
"loss": 0.1728,
|
| 388 |
+
"step": 147
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.3076923076923075,
|
| 392 |
+
"grad_norm": 1.4336873292922974,
|
| 393 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 394 |
+
"loss": 0.1802,
|
| 395 |
+
"step": 150
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.353846153846154,
|
| 399 |
+
"grad_norm": 3.3690383434295654,
|
| 400 |
+
"learning_rate": 1.2e-05,
|
| 401 |
+
"loss": 0.1739,
|
| 402 |
+
"step": 153
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.4,
|
| 406 |
+
"grad_norm": 2.487844467163086,
|
| 407 |
+
"learning_rate": 1.1142857142857143e-05,
|
| 408 |
+
"loss": 0.1215,
|
| 409 |
+
"step": 156
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.4461538461538463,
|
| 413 |
+
"grad_norm": 1.9194165468215942,
|
| 414 |
+
"learning_rate": 1.0285714285714286e-05,
|
| 415 |
+
"loss": 0.1565,
|
| 416 |
+
"step": 159
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.4923076923076923,
|
| 420 |
+
"grad_norm": 1.367956280708313,
|
| 421 |
+
"learning_rate": 9.42857142857143e-06,
|
| 422 |
+
"loss": 0.0926,
|
| 423 |
+
"step": 162
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.5384615384615383,
|
| 427 |
+
"grad_norm": 1.0028507709503174,
|
| 428 |
+
"learning_rate": 8.571428571428573e-06,
|
| 429 |
+
"loss": 0.0958,
|
| 430 |
+
"step": 165
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.5846153846153848,
|
| 434 |
+
"grad_norm": 1.140076756477356,
|
| 435 |
+
"learning_rate": 7.714285714285714e-06,
|
| 436 |
+
"loss": 0.0934,
|
| 437 |
+
"step": 168
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.6307692307692307,
|
| 441 |
+
"grad_norm": 2.3094916343688965,
|
| 442 |
+
"learning_rate": 6.857142857142858e-06,
|
| 443 |
+
"loss": 0.1129,
|
| 444 |
+
"step": 171
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.676923076923077,
|
| 448 |
+
"grad_norm": 6.090031623840332,
|
| 449 |
+
"learning_rate": 6e-06,
|
| 450 |
+
"loss": 0.1167,
|
| 451 |
+
"step": 174
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.723076923076923,
|
| 455 |
+
"grad_norm": 2.4219930171966553,
|
| 456 |
+
"learning_rate": 5.142857142857143e-06,
|
| 457 |
+
"loss": 0.1047,
|
| 458 |
+
"step": 177
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.769230769230769,
|
| 462 |
+
"grad_norm": 0.7635632157325745,
|
| 463 |
+
"learning_rate": 4.285714285714286e-06,
|
| 464 |
+
"loss": 0.1152,
|
| 465 |
+
"step": 180
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.815384615384615,
|
| 469 |
+
"grad_norm": 2.196014165878296,
|
| 470 |
+
"learning_rate": 3.428571428571429e-06,
|
| 471 |
+
"loss": 0.1047,
|
| 472 |
+
"step": 183
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.8615384615384616,
|
| 476 |
+
"grad_norm": 1.5385066270828247,
|
| 477 |
+
"learning_rate": 2.5714285714285716e-06,
|
| 478 |
+
"loss": 0.0809,
|
| 479 |
+
"step": 186
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.9076923076923076,
|
| 483 |
+
"grad_norm": 6.626975059509277,
|
| 484 |
+
"learning_rate": 1.7142857142857145e-06,
|
| 485 |
+
"loss": 0.1107,
|
| 486 |
+
"step": 189
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.953846153846154,
|
| 490 |
+
"grad_norm": 2.2722299098968506,
|
| 491 |
+
"learning_rate": 8.571428571428572e-07,
|
| 492 |
+
"loss": 0.0913,
|
| 493 |
+
"step": 192
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.0,
|
| 497 |
+
"grad_norm": 1.6369292736053467,
|
| 498 |
+
"learning_rate": 0.0,
|
| 499 |
+
"loss": 0.0974,
|
| 500 |
+
"step": 195
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.0,
|
| 504 |
+
"eval_accuracy": 1.0,
|
| 505 |
+
"eval_f1_macro": 1.0,
|
| 506 |
+
"eval_f1_micro": 1.0,
|
| 507 |
+
"eval_f1_weighted": 1.0,
|
| 508 |
+
"eval_loss": 0.052504993975162506,
|
| 509 |
+
"eval_precision_macro": 1.0,
|
| 510 |
+
"eval_precision_micro": 1.0,
|
| 511 |
+
"eval_precision_weighted": 1.0,
|
| 512 |
+
"eval_recall_macro": 1.0,
|
| 513 |
+
"eval_recall_micro": 1.0,
|
| 514 |
+
"eval_recall_weighted": 1.0,
|
| 515 |
+
"eval_runtime": 19.6807,
|
| 516 |
+
"eval_samples_per_second": 6.605,
|
| 517 |
+
"eval_steps_per_second": 0.457,
|
| 518 |
+
"step": 195
|
| 519 |
+
}
|
| 520 |
+
],
|
| 521 |
+
"logging_steps": 3,
|
| 522 |
+
"max_steps": 195,
|
| 523 |
+
"num_input_tokens_seen": 0,
|
| 524 |
+
"num_train_epochs": 3,
|
| 525 |
+
"save_steps": 500,
|
| 526 |
+
"stateful_callbacks": {
|
| 527 |
+
"EarlyStoppingCallback": {
|
| 528 |
+
"args": {
|
| 529 |
+
"early_stopping_patience": 5,
|
| 530 |
+
"early_stopping_threshold": 0.01
|
| 531 |
+
},
|
| 532 |
+
"attributes": {
|
| 533 |
+
"early_stopping_patience_counter": 0
|
| 534 |
+
}
|
| 535 |
+
},
|
| 536 |
+
"TrainerControl": {
|
| 537 |
+
"args": {
|
| 538 |
+
"should_epoch_stop": false,
|
| 539 |
+
"should_evaluate": false,
|
| 540 |
+
"should_log": false,
|
| 541 |
+
"should_save": true,
|
| 542 |
+
"should_training_stop": true
|
| 543 |
+
},
|
| 544 |
+
"attributes": {}
|
| 545 |
+
}
|
| 546 |
+
},
|
| 547 |
+
"total_flos": 102623446149120.0,
|
| 548 |
+
"train_batch_size": 8,
|
| 549 |
+
"trial_name": null,
|
| 550 |
+
"trial_params": null
|
| 551 |
+
}
|
checkpoint-195/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ccfc4d9c12918c34388a92167d63e81b8fc6db9bc12bed3a0bad506328ac99e
|
| 3 |
+
size 5112
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
+
"_num_labels": 13,
|
| 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 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "0",
|
| 16 |
+
"1": "1",
|
| 17 |
+
"2": "10",
|
| 18 |
+
"3": "11",
|
| 19 |
+
"4": "12",
|
| 20 |
+
"5": "2",
|
| 21 |
+
"6": "3",
|
| 22 |
+
"7": "4",
|
| 23 |
+
"8": "5",
|
| 24 |
+
"9": "6",
|
| 25 |
+
"10": "7",
|
| 26 |
+
"11": "8",
|
| 27 |
+
"12": "9"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"0": 0,
|
| 33 |
+
"1": 1,
|
| 34 |
+
"10": 2,
|
| 35 |
+
"11": 3,
|
| 36 |
+
"12": 4,
|
| 37 |
+
"2": 5,
|
| 38 |
+
"3": 6,
|
| 39 |
+
"4": 7,
|
| 40 |
+
"5": 8,
|
| 41 |
+
"6": 9,
|
| 42 |
+
"7": 10,
|
| 43 |
+
"8": 11,
|
| 44 |
+
"9": 12
|
| 45 |
+
},
|
| 46 |
+
"layer_norm_eps": 1e-05,
|
| 47 |
+
"max_position_embeddings": 514,
|
| 48 |
+
"model_type": "roberta",
|
| 49 |
+
"num_attention_heads": 12,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"problem_type": "single_label_classification",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.41.2",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
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 sha256:689d6073a6d72a9f9ed6c12c58c78d524bdc14a41e79574a6bdf30744306299f
|
| 3 |
+
size 498646660
|
runs/Jun19_22-00-52_r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh/events.out.tfevents.1718834454.r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh.329.0
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 sha256:0e75017f2c2991618ca8d35e73169df258fdadb672d5a9beac5c111bb4cd6646
|
| 3 |
+
size 21647
|
runs/Jun19_22-00-52_r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh/events.out.tfevents.1718835429.r-stepharn-roberta-opt-v2-vntpt72b-13120-71wdh.329.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6cbd00affe7c90900c1d2eff4daca128ea0d4036d28f29d5fd18facb67a7c2f
|
| 3 |
+
size 921
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
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": 512,
|
| 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 sha256:6ccfc4d9c12918c34388a92167d63e81b8fc6db9bc12bed3a0bad506328ac99e
|
| 3 |
+
size 5112
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "RobertaArmControl/autotrain-data",
|
| 3 |
+
"model": "FacebookAI/roberta-base",
|
| 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": "RobertaArmControl",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "none",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"eval_strategy": "epoch",
|
| 26 |
+
"username": "StephArn",
|
| 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
|
|
|