Instructions to use joseph10/tiny-bert-sst2-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joseph10/tiny-bert-sst2-distilled with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="joseph10/tiny-bert-sst2-distilled")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("joseph10/tiny-bert-sst2-distilled") model = AutoModelForSequenceClassification.from_pretrained("joseph10/tiny-bert-sst2-distilled") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files- logs/events.out.tfevents.1701813171.joseph_legion.26688.27 +3 -0
- logs/events.out.tfevents.1701813226.joseph_legion.26688.28 +3 -0
- logs/events.out.tfevents.1701813284.joseph_legion.26688.29 +3 -0
- logs/events.out.tfevents.1701813340.joseph_legion.26688.30 +3 -0
- model.safetensors +1 -1
- run-29/checkpoint-958/config.json +38 -0
- run-29/checkpoint-958/model.safetensors +3 -0
- run-29/checkpoint-958/optimizer.pt +3 -0
- run-29/checkpoint-958/rng_state.pth +3 -0
- run-29/checkpoint-958/scheduler.pt +3 -0
- run-29/checkpoint-958/special_tokens_map.json +7 -0
- run-29/checkpoint-958/tokenizer.json +0 -0
- run-29/checkpoint-958/tokenizer_config.json +57 -0
- run-29/checkpoint-958/trainer_state.json +39 -0
- run-29/checkpoint-958/training_args.bin +3 -0
- run-29/checkpoint-958/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1701813171.joseph_legion.26688.27
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fccb6201a6cef8b19d2717a8650be749c03a4fdbafebe0f5a561a1034f0798d3
|
| 3 |
+
size 4845
|
logs/events.out.tfevents.1701813226.joseph_legion.26688.28
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5efc07415a83360c2e91b3287dbafbfce7a0822bdd14fe99edd085a202c12a05
|
| 3 |
+
size 4845
|
logs/events.out.tfevents.1701813284.joseph_legion.26688.29
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bef55a4c69ebe197cc0944604583a8901234df8cea963b4fe13953ec91f16dc2
|
| 3 |
+
size 4846
|
logs/events.out.tfevents.1701813340.joseph_legion.26688.30
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a82d860e58826c8a59fe8ead57a8d955cadcf7af2b23549c91500ad2da205a
|
| 3 |
+
size 4843
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17550344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad41bdddf4036c746fc277f66904b63e383af2452f1fc2aaa86bbae16f6d44f
|
| 3 |
size 17550344
|
run-29/checkpoint-958/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "noHate",
|
| 13 |
+
"1": "hate",
|
| 14 |
+
"2": "idk/skip",
|
| 15 |
+
"3": "relation"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 512,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"hate": "1",
|
| 21 |
+
"idk/skip": "2",
|
| 22 |
+
"noHate": "0",
|
| 23 |
+
"relation": "3"
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 2,
|
| 29 |
+
"num_hidden_layers": 2,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.35.2",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
run-29/checkpoint-958/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad41bdddf4036c746fc277f66904b63e383af2452f1fc2aaa86bbae16f6d44f
|
| 3 |
+
size 17550344
|
run-29/checkpoint-958/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb3c6b741985d4b0a013aa3d13ed586f84fecd9f7c65a4e380e37744fdf1488
|
| 3 |
+
size 35125946
|
run-29/checkpoint-958/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f018c83e7d459254f51934df148aa123d7614799807eb3b0b54b2806a9f0ecb
|
| 3 |
+
size 14308
|
run-29/checkpoint-958/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6d5fa1b81c9eba3c31d99fea72b00f96148013af87cfd67f5fdedfed51243b3
|
| 3 |
+
size 1064
|
run-29/checkpoint-958/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-29/checkpoint-958/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-29/checkpoint-958/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
run-29/checkpoint-958/trainer_state.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8665447897623401,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled\\run-29\\checkpoint-958",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 958,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 5.513486814183312e-05,
|
| 14 |
+
"loss": 0.4752,
|
| 15 |
+
"step": 958
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.8665447897623401,
|
| 20 |
+
"eval_loss": 0.46969035267829895,
|
| 21 |
+
"eval_runtime": 28.1738,
|
| 22 |
+
"eval_samples_per_second": 77.661,
|
| 23 |
+
"eval_steps_per_second": 0.639,
|
| 24 |
+
"step": 958
|
| 25 |
+
}
|
| 26 |
+
],
|
| 27 |
+
"logging_steps": 500,
|
| 28 |
+
"max_steps": 4790,
|
| 29 |
+
"num_train_epochs": 5,
|
| 30 |
+
"save_steps": 500,
|
| 31 |
+
"total_flos": 990525458304.0,
|
| 32 |
+
"trial_name": null,
|
| 33 |
+
"trial_params": {
|
| 34 |
+
"learning_rate": 6.89185851772914e-05,
|
| 35 |
+
"num_train_epochs": 5,
|
| 36 |
+
"per_device_train_batch_size": 8,
|
| 37 |
+
"seed": 29
|
| 38 |
+
}
|
| 39 |
+
}
|
run-29/checkpoint-958/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fd897500dbcee0a0d1c4035b4955589ca6dec53bda6fcdc6d36368264516ac9
|
| 3 |
+
size 4664
|
run-29/checkpoint-958/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fd897500dbcee0a0d1c4035b4955589ca6dec53bda6fcdc6d36368264516ac9
|
| 3 |
size 4664
|