tweetpy commited on
Upload 8 files
Browse files- config.json +37 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- trainer_state.json +417 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ctoraman/hate-speech-bert",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.37.2",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2485e36c917c21bf2edd0f33c8e0bebb0bad902b11b0ff6f7a34eaeed8cd27de
|
| 3 |
+
size 437961724
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"max_length": 512,
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_to_multiple_of": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"pad_token_type_id": 0,
|
| 53 |
+
"padding_side": "right",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"tokenize_chinese_chars": true,
|
| 58 |
+
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "[UNK]"
|
| 62 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.88997555012225,
|
| 5 |
+
"eval_steps": 800,
|
| 6 |
+
"global_step": 18000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.22,
|
| 13 |
+
"learning_rate": 4.7826677533279e-05,
|
| 14 |
+
"loss": 0.3854,
|
| 15 |
+
"step": 800
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.22,
|
| 19 |
+
"eval_accuracy": 0.8774075206358911,
|
| 20 |
+
"eval_f1-score": 0.8772242175124827,
|
| 21 |
+
"eval_loss": 0.3071616590023041,
|
| 22 |
+
"eval_precision": 0.8794550305873866,
|
| 23 |
+
"eval_recall": 0.8774075206358911,
|
| 24 |
+
"eval_runtime": 64.5762,
|
| 25 |
+
"eval_samples_per_second": 50.653,
|
| 26 |
+
"eval_steps_per_second": 6.334,
|
| 27 |
+
"step": 800
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.43,
|
| 31 |
+
"learning_rate": 4.5653355066558e-05,
|
| 32 |
+
"loss": 0.3445,
|
| 33 |
+
"step": 1600
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.43,
|
| 37 |
+
"eval_accuracy": 0.9003362885967594,
|
| 38 |
+
"eval_f1-score": 0.9003365494138151,
|
| 39 |
+
"eval_loss": 0.27588778734207153,
|
| 40 |
+
"eval_precision": 0.9003395029663702,
|
| 41 |
+
"eval_recall": 0.9003362885967594,
|
| 42 |
+
"eval_runtime": 60.4968,
|
| 43 |
+
"eval_samples_per_second": 54.069,
|
| 44 |
+
"eval_steps_per_second": 6.761,
|
| 45 |
+
"step": 1600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.65,
|
| 49 |
+
"learning_rate": 4.3480032599837e-05,
|
| 50 |
+
"loss": 0.3277,
|
| 51 |
+
"step": 2400
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.65,
|
| 55 |
+
"eval_accuracy": 0.8969734026291654,
|
| 56 |
+
"eval_f1-score": 0.8969608633994076,
|
| 57 |
+
"eval_loss": 0.288944274187088,
|
| 58 |
+
"eval_precision": 0.8971095244147143,
|
| 59 |
+
"eval_recall": 0.8969734026291654,
|
| 60 |
+
"eval_runtime": 60.3986,
|
| 61 |
+
"eval_samples_per_second": 54.157,
|
| 62 |
+
"eval_steps_per_second": 6.772,
|
| 63 |
+
"step": 2400
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.87,
|
| 67 |
+
"learning_rate": 4.130671013311601e-05,
|
| 68 |
+
"loss": 0.3222,
|
| 69 |
+
"step": 3200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.87,
|
| 73 |
+
"eval_accuracy": 0.9046163252827881,
|
| 74 |
+
"eval_f1-score": 0.9045643986899728,
|
| 75 |
+
"eval_loss": 0.3288567364215851,
|
| 76 |
+
"eval_precision": 0.9056517879747317,
|
| 77 |
+
"eval_recall": 0.9046163252827881,
|
| 78 |
+
"eval_runtime": 60.7827,
|
| 79 |
+
"eval_samples_per_second": 53.815,
|
| 80 |
+
"eval_steps_per_second": 6.729,
|
| 81 |
+
"step": 3200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.09,
|
| 85 |
+
"learning_rate": 3.9133387666395004e-05,
|
| 86 |
+
"loss": 0.2717,
|
| 87 |
+
"step": 4000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.09,
|
| 91 |
+
"eval_accuracy": 0.9021705900336289,
|
| 92 |
+
"eval_f1-score": 0.9020992071629579,
|
| 93 |
+
"eval_loss": 0.42761483788490295,
|
| 94 |
+
"eval_precision": 0.9035219658491396,
|
| 95 |
+
"eval_recall": 0.9021705900336289,
|
| 96 |
+
"eval_runtime": 62.9323,
|
| 97 |
+
"eval_samples_per_second": 51.976,
|
| 98 |
+
"eval_steps_per_second": 6.499,
|
| 99 |
+
"step": 4000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.3,
|
| 103 |
+
"learning_rate": 3.696006519967401e-05,
|
| 104 |
+
"loss": 0.2167,
|
| 105 |
+
"step": 4800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.3,
|
| 109 |
+
"eval_accuracy": 0.908590645062672,
|
| 110 |
+
"eval_f1-score": 0.9085664450086591,
|
| 111 |
+
"eval_loss": 0.4045434892177582,
|
| 112 |
+
"eval_precision": 0.9091340460574109,
|
| 113 |
+
"eval_recall": 0.908590645062672,
|
| 114 |
+
"eval_runtime": 61.45,
|
| 115 |
+
"eval_samples_per_second": 53.23,
|
| 116 |
+
"eval_steps_per_second": 6.656,
|
| 117 |
+
"step": 4800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.52,
|
| 121 |
+
"learning_rate": 3.4786742732953e-05,
|
| 122 |
+
"loss": 0.2092,
|
| 123 |
+
"step": 5600
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.52,
|
| 127 |
+
"eval_accuracy": 0.9116478141241211,
|
| 128 |
+
"eval_f1-score": 0.9116147566351114,
|
| 129 |
+
"eval_loss": 0.3573218584060669,
|
| 130 |
+
"eval_precision": 0.9123941687742838,
|
| 131 |
+
"eval_recall": 0.9116478141241211,
|
| 132 |
+
"eval_runtime": 62.314,
|
| 133 |
+
"eval_samples_per_second": 52.492,
|
| 134 |
+
"eval_steps_per_second": 6.564,
|
| 135 |
+
"step": 5600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.74,
|
| 139 |
+
"learning_rate": 3.2613420266232006e-05,
|
| 140 |
+
"loss": 0.2062,
|
| 141 |
+
"step": 6400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.74,
|
| 145 |
+
"eval_accuracy": 0.904922042188933,
|
| 146 |
+
"eval_f1-score": 0.9049222910044366,
|
| 147 |
+
"eval_loss": 0.3768712878227234,
|
| 148 |
+
"eval_precision": 0.9049308283306433,
|
| 149 |
+
"eval_recall": 0.904922042188933,
|
| 150 |
+
"eval_runtime": 63.1267,
|
| 151 |
+
"eval_samples_per_second": 51.816,
|
| 152 |
+
"eval_steps_per_second": 6.479,
|
| 153 |
+
"step": 6400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.96,
|
| 157 |
+
"learning_rate": 3.0440097799511003e-05,
|
| 158 |
+
"loss": 0.2254,
|
| 159 |
+
"step": 7200
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.96,
|
| 163 |
+
"eval_accuracy": 0.908590645062672,
|
| 164 |
+
"eval_f1-score": 0.9084747894886354,
|
| 165 |
+
"eval_loss": 0.4190152585506439,
|
| 166 |
+
"eval_precision": 0.910461333213157,
|
| 167 |
+
"eval_recall": 0.908590645062672,
|
| 168 |
+
"eval_runtime": 61.865,
|
| 169 |
+
"eval_samples_per_second": 52.873,
|
| 170 |
+
"eval_steps_per_second": 6.611,
|
| 171 |
+
"step": 7200
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.17,
|
| 175 |
+
"learning_rate": 2.8266775332790002e-05,
|
| 176 |
+
"loss": 0.1289,
|
| 177 |
+
"step": 8000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.17,
|
| 181 |
+
"eval_accuracy": 0.8994191378783247,
|
| 182 |
+
"eval_f1-score": 0.8992916579992009,
|
| 183 |
+
"eval_loss": 0.5542723536491394,
|
| 184 |
+
"eval_precision": 0.9012452606359794,
|
| 185 |
+
"eval_recall": 0.8994191378783247,
|
| 186 |
+
"eval_runtime": 62.1736,
|
| 187 |
+
"eval_samples_per_second": 52.611,
|
| 188 |
+
"eval_steps_per_second": 6.578,
|
| 189 |
+
"step": 8000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.39,
|
| 193 |
+
"learning_rate": 2.6093452866069005e-05,
|
| 194 |
+
"loss": 0.1046,
|
| 195 |
+
"step": 8800
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.39,
|
| 199 |
+
"eval_accuracy": 0.9134821155609906,
|
| 200 |
+
"eval_f1-score": 0.9134820185252122,
|
| 201 |
+
"eval_loss": 0.4697829782962799,
|
| 202 |
+
"eval_precision": 0.9134820922449185,
|
| 203 |
+
"eval_recall": 0.9134821155609906,
|
| 204 |
+
"eval_runtime": 62.1014,
|
| 205 |
+
"eval_samples_per_second": 52.672,
|
| 206 |
+
"eval_steps_per_second": 6.586,
|
| 207 |
+
"step": 8800
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.61,
|
| 211 |
+
"learning_rate": 2.3920130399348005e-05,
|
| 212 |
+
"loss": 0.1257,
|
| 213 |
+
"step": 9600
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.61,
|
| 217 |
+
"eval_accuracy": 0.9131763986548456,
|
| 218 |
+
"eval_f1-score": 0.9131764798026453,
|
| 219 |
+
"eval_loss": 0.4252018332481384,
|
| 220 |
+
"eval_precision": 0.9131936306903841,
|
| 221 |
+
"eval_recall": 0.9131763986548456,
|
| 222 |
+
"eval_runtime": 63.346,
|
| 223 |
+
"eval_samples_per_second": 51.637,
|
| 224 |
+
"eval_steps_per_second": 6.457,
|
| 225 |
+
"step": 9600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.83,
|
| 229 |
+
"learning_rate": 2.1746807932627005e-05,
|
| 230 |
+
"loss": 0.1132,
|
| 231 |
+
"step": 10400
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.83,
|
| 235 |
+
"eval_accuracy": 0.9131763986548456,
|
| 236 |
+
"eval_f1-score": 0.9131652307887081,
|
| 237 |
+
"eval_loss": 0.42821380496025085,
|
| 238 |
+
"eval_precision": 0.9133289397789441,
|
| 239 |
+
"eval_recall": 0.9131763986548456,
|
| 240 |
+
"eval_runtime": 63.3473,
|
| 241 |
+
"eval_samples_per_second": 51.636,
|
| 242 |
+
"eval_steps_per_second": 6.456,
|
| 243 |
+
"step": 10400
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.04,
|
| 247 |
+
"learning_rate": 1.9573485465906004e-05,
|
| 248 |
+
"loss": 0.0964,
|
| 249 |
+
"step": 11200
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.04,
|
| 253 |
+
"eval_accuracy": 0.9162335677162947,
|
| 254 |
+
"eval_f1-score": 0.9162321584770682,
|
| 255 |
+
"eval_loss": 0.5392835140228271,
|
| 256 |
+
"eval_precision": 0.9162992614461799,
|
| 257 |
+
"eval_recall": 0.9162335677162947,
|
| 258 |
+
"eval_runtime": 61.748,
|
| 259 |
+
"eval_samples_per_second": 52.973,
|
| 260 |
+
"eval_steps_per_second": 6.624,
|
| 261 |
+
"step": 11200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.26,
|
| 265 |
+
"learning_rate": 1.7400162999185004e-05,
|
| 266 |
+
"loss": 0.0476,
|
| 267 |
+
"step": 12000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.26,
|
| 271 |
+
"eval_accuracy": 0.9177621522470193,
|
| 272 |
+
"eval_f1-score": 0.9177552338454668,
|
| 273 |
+
"eval_loss": 0.5539752244949341,
|
| 274 |
+
"eval_precision": 0.9178555704146932,
|
| 275 |
+
"eval_recall": 0.9177621522470193,
|
| 276 |
+
"eval_runtime": 62.8946,
|
| 277 |
+
"eval_samples_per_second": 52.008,
|
| 278 |
+
"eval_steps_per_second": 6.503,
|
| 279 |
+
"step": 12000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.48,
|
| 283 |
+
"learning_rate": 1.5226840532464004e-05,
|
| 284 |
+
"loss": 0.0436,
|
| 285 |
+
"step": 12800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.48,
|
| 289 |
+
"eval_accuracy": 0.9128706817487007,
|
| 290 |
+
"eval_f1-score": 0.9128070948010026,
|
| 291 |
+
"eval_loss": 0.5679276585578918,
|
| 292 |
+
"eval_precision": 0.9139222236120726,
|
| 293 |
+
"eval_recall": 0.9128706817487007,
|
| 294 |
+
"eval_runtime": 62.7176,
|
| 295 |
+
"eval_samples_per_second": 52.154,
|
| 296 |
+
"eval_steps_per_second": 6.521,
|
| 297 |
+
"step": 12800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.69,
|
| 301 |
+
"learning_rate": 1.3053518065743007e-05,
|
| 302 |
+
"loss": 0.0582,
|
| 303 |
+
"step": 13600
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.69,
|
| 307 |
+
"eval_accuracy": 0.9153164169978599,
|
| 308 |
+
"eval_f1-score": 0.9152738804862125,
|
| 309 |
+
"eval_loss": 0.5282616019248962,
|
| 310 |
+
"eval_precision": 0.9163011804874139,
|
| 311 |
+
"eval_recall": 0.9153164169978599,
|
| 312 |
+
"eval_runtime": 62.1777,
|
| 313 |
+
"eval_samples_per_second": 52.607,
|
| 314 |
+
"eval_steps_per_second": 6.578,
|
| 315 |
+
"step": 13600
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.91,
|
| 319 |
+
"learning_rate": 1.0880195599022006e-05,
|
| 320 |
+
"loss": 0.0478,
|
| 321 |
+
"step": 14400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.91,
|
| 325 |
+
"eval_accuracy": 0.9159278508101498,
|
| 326 |
+
"eval_f1-score": 0.9159151975384024,
|
| 327 |
+
"eval_loss": 0.5375821590423584,
|
| 328 |
+
"eval_precision": 0.9161123951905313,
|
| 329 |
+
"eval_recall": 0.9159278508101498,
|
| 330 |
+
"eval_runtime": 64.9703,
|
| 331 |
+
"eval_samples_per_second": 50.346,
|
| 332 |
+
"eval_steps_per_second": 6.295,
|
| 333 |
+
"step": 14400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.13,
|
| 337 |
+
"learning_rate": 8.706873132301006e-06,
|
| 338 |
+
"loss": 0.0379,
|
| 339 |
+
"step": 15200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.13,
|
| 343 |
+
"eval_accuracy": 0.9159278508101498,
|
| 344 |
+
"eval_f1-score": 0.9158993160297756,
|
| 345 |
+
"eval_loss": 0.5539520978927612,
|
| 346 |
+
"eval_precision": 0.916389347487138,
|
| 347 |
+
"eval_recall": 0.9159278508101498,
|
| 348 |
+
"eval_runtime": 61.7598,
|
| 349 |
+
"eval_samples_per_second": 52.963,
|
| 350 |
+
"eval_steps_per_second": 6.622,
|
| 351 |
+
"step": 15200
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.35,
|
| 355 |
+
"learning_rate": 6.5335506655800055e-06,
|
| 356 |
+
"loss": 0.0198,
|
| 357 |
+
"step": 16000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.35,
|
| 361 |
+
"eval_accuracy": 0.9143992662794252,
|
| 362 |
+
"eval_f1-score": 0.9143978261809456,
|
| 363 |
+
"eval_loss": 0.6111006140708923,
|
| 364 |
+
"eval_precision": 0.9144647611244408,
|
| 365 |
+
"eval_recall": 0.9143992662794252,
|
| 366 |
+
"eval_runtime": 63.6411,
|
| 367 |
+
"eval_samples_per_second": 51.398,
|
| 368 |
+
"eval_steps_per_second": 6.427,
|
| 369 |
+
"step": 16000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.56,
|
| 373 |
+
"learning_rate": 4.360228198859006e-06,
|
| 374 |
+
"loss": 0.0195,
|
| 375 |
+
"step": 16800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.56,
|
| 379 |
+
"eval_accuracy": 0.9159278508101498,
|
| 380 |
+
"eval_f1-score": 0.915924110308607,
|
| 381 |
+
"eval_loss": 0.5844493508338928,
|
| 382 |
+
"eval_precision": 0.9159698581146932,
|
| 383 |
+
"eval_recall": 0.9159278508101498,
|
| 384 |
+
"eval_runtime": 63.4625,
|
| 385 |
+
"eval_samples_per_second": 51.542,
|
| 386 |
+
"eval_steps_per_second": 6.445,
|
| 387 |
+
"step": 16800
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.78,
|
| 391 |
+
"learning_rate": 2.186905732138006e-06,
|
| 392 |
+
"loss": 0.0189,
|
| 393 |
+
"step": 17600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.78,
|
| 397 |
+
"eval_accuracy": 0.9174564353408744,
|
| 398 |
+
"eval_f1-score": 0.9174563427638073,
|
| 399 |
+
"eval_loss": 0.5772590637207031,
|
| 400 |
+
"eval_precision": 0.917480946018594,
|
| 401 |
+
"eval_recall": 0.9174564353408744,
|
| 402 |
+
"eval_runtime": 62.6716,
|
| 403 |
+
"eval_samples_per_second": 52.193,
|
| 404 |
+
"eval_steps_per_second": 6.526,
|
| 405 |
+
"step": 17600
|
| 406 |
+
}
|
| 407 |
+
],
|
| 408 |
+
"logging_steps": 800,
|
| 409 |
+
"max_steps": 18405,
|
| 410 |
+
"num_input_tokens_seen": 0,
|
| 411 |
+
"num_train_epochs": 5,
|
| 412 |
+
"save_steps": 500,
|
| 413 |
+
"total_flos": 3.788201743080653e+16,
|
| 414 |
+
"train_batch_size": 8,
|
| 415 |
+
"trial_name": null,
|
| 416 |
+
"trial_params": null
|
| 417 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf620551381deb4a4ebe569f68450cb79d20342038644c05878cfd910cbccbdd
|
| 3 |
+
size 4664
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|