Upload folder using huggingface_hub
Browse files- config.json +59 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- trainer_state.json +340 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_position_embeddings": true,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.01,
|
| 29 |
+
"intermediate_size": 3072,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"LABEL_0": 0,
|
| 32 |
+
"LABEL_1": 1,
|
| 33 |
+
"LABEL_10": 10,
|
| 34 |
+
"LABEL_11": 11,
|
| 35 |
+
"LABEL_12": 12,
|
| 36 |
+
"LABEL_13": 13,
|
| 37 |
+
"LABEL_14": 14,
|
| 38 |
+
"LABEL_2": 2,
|
| 39 |
+
"LABEL_3": 3,
|
| 40 |
+
"LABEL_4": 4,
|
| 41 |
+
"LABEL_5": 5,
|
| 42 |
+
"LABEL_6": 6,
|
| 43 |
+
"LABEL_7": 7,
|
| 44 |
+
"LABEL_8": 8,
|
| 45 |
+
"LABEL_9": 9
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-12,
|
| 48 |
+
"max_position_embeddings": 512,
|
| 49 |
+
"model_type": "bert",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"pad_token_id": 4,
|
| 53 |
+
"position_embedding_type": "relative_key_query",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.51.3",
|
| 56 |
+
"type_vocab_size": 2,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50000
|
| 59 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a96f6341feda31f59181f8c8ab87447aa863cfff31dc2bb1030769ab72c6f7c9
|
| 3 |
+
size 498616780
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[SEP]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[UNK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[MASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[PAD]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_text": false,
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": true,
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": false,
|
| 56 |
+
"tokenize_chinese_chars": false,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 17000,
|
| 3 |
+
"best_metric": 0.8946104799920928,
|
| 4 |
+
"best_model_checkpoint": "banBERT-Base-pos/checkpoint-17000",
|
| 5 |
+
"epoch": 0.9946755602363817,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 17000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.05851032707272834,
|
| 14 |
+
"grad_norm": 4.870177745819092,
|
| 15 |
+
"learning_rate": 4.952324665090623e-05,
|
| 16 |
+
"loss": 0.5681,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05851032707272834,
|
| 21 |
+
"eval_f1": 0.8762604390800369,
|
| 22 |
+
"eval_loss": 0.26431742310523987,
|
| 23 |
+
"eval_precision": 0.8742650838051628,
|
| 24 |
+
"eval_recall": 0.8796261556029517,
|
| 25 |
+
"eval_runtime": 28.9994,
|
| 26 |
+
"eval_samples_per_second": 261.178,
|
| 27 |
+
"eval_steps_per_second": 32.656,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.11702065414545668,
|
| 32 |
+
"grad_norm": 6.504812240600586,
|
| 33 |
+
"learning_rate": 4.853821907013397e-05,
|
| 34 |
+
"loss": 0.2821,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.11702065414545668,
|
| 39 |
+
"eval_f1": 0.8747857038906649,
|
| 40 |
+
"eval_loss": 0.2531687021255493,
|
| 41 |
+
"eval_precision": 0.8826666555035545,
|
| 42 |
+
"eval_recall": 0.8742214967913846,
|
| 43 |
+
"eval_runtime": 29.3663,
|
| 44 |
+
"eval_samples_per_second": 257.915,
|
| 45 |
+
"eval_steps_per_second": 32.248,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.175530981218185,
|
| 50 |
+
"grad_norm": 2.781933307647705,
|
| 51 |
+
"learning_rate": 4.7553191489361704e-05,
|
| 52 |
+
"loss": 0.2697,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.175530981218185,
|
| 57 |
+
"eval_f1": 0.8666467093588278,
|
| 58 |
+
"eval_loss": 0.2597614824771881,
|
| 59 |
+
"eval_precision": 0.8736361925736554,
|
| 60 |
+
"eval_recall": 0.8661208831213065,
|
| 61 |
+
"eval_runtime": 29.0115,
|
| 62 |
+
"eval_samples_per_second": 261.068,
|
| 63 |
+
"eval_steps_per_second": 32.642,
|
| 64 |
+
"step": 3000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.23404130829091335,
|
| 68 |
+
"grad_norm": 3.3094711303710938,
|
| 69 |
+
"learning_rate": 4.656816390858944e-05,
|
| 70 |
+
"loss": 0.2659,
|
| 71 |
+
"step": 4000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.23404130829091335,
|
| 75 |
+
"eval_f1": 0.8798149861336466,
|
| 76 |
+
"eval_loss": 0.24752835929393768,
|
| 77 |
+
"eval_precision": 0.8764034593493383,
|
| 78 |
+
"eval_recall": 0.8851085241178042,
|
| 79 |
+
"eval_runtime": 29.6951,
|
| 80 |
+
"eval_samples_per_second": 255.059,
|
| 81 |
+
"eval_steps_per_second": 31.891,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.2925516353636417,
|
| 86 |
+
"grad_norm": 2.068115234375,
|
| 87 |
+
"learning_rate": 4.5583136327817186e-05,
|
| 88 |
+
"loss": 0.2608,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.2925516353636417,
|
| 93 |
+
"eval_f1": 0.8836360762583084,
|
| 94 |
+
"eval_loss": 0.23901157081127167,
|
| 95 |
+
"eval_precision": 0.8866831487439992,
|
| 96 |
+
"eval_recall": 0.8816467698684325,
|
| 97 |
+
"eval_runtime": 29.6967,
|
| 98 |
+
"eval_samples_per_second": 255.046,
|
| 99 |
+
"eval_steps_per_second": 31.889,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.35106196243637,
|
| 104 |
+
"grad_norm": 2.984527111053467,
|
| 105 |
+
"learning_rate": 4.459810874704492e-05,
|
| 106 |
+
"loss": 0.2548,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.35106196243637,
|
| 111 |
+
"eval_f1": 0.8786857503892376,
|
| 112 |
+
"eval_loss": 0.24374601244926453,
|
| 113 |
+
"eval_precision": 0.8808030269623512,
|
| 114 |
+
"eval_recall": 0.878183658913097,
|
| 115 |
+
"eval_runtime": 29.5386,
|
| 116 |
+
"eval_samples_per_second": 256.41,
|
| 117 |
+
"eval_steps_per_second": 32.06,
|
| 118 |
+
"step": 6000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.40957228950909835,
|
| 122 |
+
"grad_norm": 3.5354621410369873,
|
| 123 |
+
"learning_rate": 4.3613081166272655e-05,
|
| 124 |
+
"loss": 0.2535,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.40957228950909835,
|
| 129 |
+
"eval_f1": 0.8885007809186033,
|
| 130 |
+
"eval_loss": 0.23431703448295593,
|
| 131 |
+
"eval_precision": 0.8823384881830838,
|
| 132 |
+
"eval_recall": 0.8961195227790774,
|
| 133 |
+
"eval_runtime": 28.9987,
|
| 134 |
+
"eval_samples_per_second": 261.184,
|
| 135 |
+
"eval_steps_per_second": 32.657,
|
| 136 |
+
"step": 7000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4680826165818267,
|
| 140 |
+
"grad_norm": 3.906360626220703,
|
| 141 |
+
"learning_rate": 4.2628053585500396e-05,
|
| 142 |
+
"loss": 0.255,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4680826165818267,
|
| 147 |
+
"eval_f1": 0.8796937707178186,
|
| 148 |
+
"eval_loss": 0.23554810881614685,
|
| 149 |
+
"eval_precision": 0.8812208287855526,
|
| 150 |
+
"eval_recall": 0.880771461292737,
|
| 151 |
+
"eval_runtime": 30.6899,
|
| 152 |
+
"eval_samples_per_second": 246.791,
|
| 153 |
+
"eval_steps_per_second": 30.857,
|
| 154 |
+
"step": 8000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.526592943654555,
|
| 158 |
+
"grad_norm": 3.616974353790283,
|
| 159 |
+
"learning_rate": 4.1644011032308906e-05,
|
| 160 |
+
"loss": 0.2457,
|
| 161 |
+
"step": 9000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.526592943654555,
|
| 165 |
+
"eval_f1": 0.8853991026903275,
|
| 166 |
+
"eval_loss": 0.2313537746667862,
|
| 167 |
+
"eval_precision": 0.8879722004510241,
|
| 168 |
+
"eval_recall": 0.8847937369742619,
|
| 169 |
+
"eval_runtime": 29.3159,
|
| 170 |
+
"eval_samples_per_second": 258.358,
|
| 171 |
+
"eval_steps_per_second": 32.303,
|
| 172 |
+
"step": 9000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.5851032707272834,
|
| 176 |
+
"grad_norm": 3.81512713432312,
|
| 177 |
+
"learning_rate": 4.065898345153665e-05,
|
| 178 |
+
"loss": 0.2527,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.5851032707272834,
|
| 183 |
+
"eval_f1": 0.8797925096491191,
|
| 184 |
+
"eval_loss": 0.2423781007528305,
|
| 185 |
+
"eval_precision": 0.8750872391747755,
|
| 186 |
+
"eval_recall": 0.8881566716696347,
|
| 187 |
+
"eval_runtime": 30.0187,
|
| 188 |
+
"eval_samples_per_second": 252.31,
|
| 189 |
+
"eval_steps_per_second": 31.547,
|
| 190 |
+
"step": 10000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.6436135978000117,
|
| 194 |
+
"grad_norm": 2.189429521560669,
|
| 195 |
+
"learning_rate": 3.967494089834515e-05,
|
| 196 |
+
"loss": 0.2446,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.6436135978000117,
|
| 201 |
+
"eval_f1": 0.8923392397004614,
|
| 202 |
+
"eval_loss": 0.22613154351711273,
|
| 203 |
+
"eval_precision": 0.8840821992199377,
|
| 204 |
+
"eval_recall": 0.9019369581982146,
|
| 205 |
+
"eval_runtime": 30.4237,
|
| 206 |
+
"eval_samples_per_second": 248.951,
|
| 207 |
+
"eval_steps_per_second": 31.127,
|
| 208 |
+
"step": 11000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.70212392487274,
|
| 212 |
+
"grad_norm": 3.8916683197021484,
|
| 213 |
+
"learning_rate": 3.86899133175729e-05,
|
| 214 |
+
"loss": 0.2496,
|
| 215 |
+
"step": 12000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.70212392487274,
|
| 219 |
+
"eval_f1": 0.8838883711908031,
|
| 220 |
+
"eval_loss": 0.2282320261001587,
|
| 221 |
+
"eval_precision": 0.8870449139456895,
|
| 222 |
+
"eval_recall": 0.881842969912727,
|
| 223 |
+
"eval_runtime": 28.9189,
|
| 224 |
+
"eval_samples_per_second": 261.905,
|
| 225 |
+
"eval_steps_per_second": 32.747,
|
| 226 |
+
"step": 12000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7606342519454684,
|
| 230 |
+
"grad_norm": 2.145176887512207,
|
| 231 |
+
"learning_rate": 3.770587076438141e-05,
|
| 232 |
+
"loss": 0.2439,
|
| 233 |
+
"step": 13000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7606342519454684,
|
| 237 |
+
"eval_f1": 0.8769622250324842,
|
| 238 |
+
"eval_loss": 0.2252449244260788,
|
| 239 |
+
"eval_precision": 0.887928073773863,
|
| 240 |
+
"eval_recall": 0.8695732334120527,
|
| 241 |
+
"eval_runtime": 29.4593,
|
| 242 |
+
"eval_samples_per_second": 257.1,
|
| 243 |
+
"eval_steps_per_second": 32.146,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8191445790181967,
|
| 248 |
+
"grad_norm": 1.7703274488449097,
|
| 249 |
+
"learning_rate": 3.672084318360914e-05,
|
| 250 |
+
"loss": 0.243,
|
| 251 |
+
"step": 14000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.8191445790181967,
|
| 255 |
+
"eval_f1": 0.879454001823476,
|
| 256 |
+
"eval_loss": 0.22599145770072937,
|
| 257 |
+
"eval_precision": 0.8828080832134976,
|
| 258 |
+
"eval_recall": 0.8786664905760042,
|
| 259 |
+
"eval_runtime": 29.753,
|
| 260 |
+
"eval_samples_per_second": 254.562,
|
| 261 |
+
"eval_steps_per_second": 31.829,
|
| 262 |
+
"step": 14000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.877654906090925,
|
| 266 |
+
"grad_norm": 4.403445243835449,
|
| 267 |
+
"learning_rate": 3.573581560283688e-05,
|
| 268 |
+
"loss": 0.2427,
|
| 269 |
+
"step": 15000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.877654906090925,
|
| 273 |
+
"eval_f1": 0.8888557192580028,
|
| 274 |
+
"eval_loss": 0.22790007293224335,
|
| 275 |
+
"eval_precision": 0.8901524013282429,
|
| 276 |
+
"eval_recall": 0.8884489266872372,
|
| 277 |
+
"eval_runtime": 31.5334,
|
| 278 |
+
"eval_samples_per_second": 240.19,
|
| 279 |
+
"eval_steps_per_second": 30.032,
|
| 280 |
+
"step": 15000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.9361652331636534,
|
| 284 |
+
"grad_norm": 6.978273868560791,
|
| 285 |
+
"learning_rate": 3.4751773049645395e-05,
|
| 286 |
+
"loss": 0.2371,
|
| 287 |
+
"step": 16000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.9361652331636534,
|
| 291 |
+
"eval_f1": 0.8933984344595972,
|
| 292 |
+
"eval_loss": 0.22917409241199493,
|
| 293 |
+
"eval_precision": 0.8891663922870625,
|
| 294 |
+
"eval_recall": 0.8998411225843156,
|
| 295 |
+
"eval_runtime": 29.6746,
|
| 296 |
+
"eval_samples_per_second": 255.235,
|
| 297 |
+
"eval_steps_per_second": 31.913,
|
| 298 |
+
"step": 16000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.9946755602363817,
|
| 302 |
+
"grad_norm": 4.8312859535217285,
|
| 303 |
+
"learning_rate": 3.376674546887313e-05,
|
| 304 |
+
"loss": 0.2405,
|
| 305 |
+
"step": 17000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.9946755602363817,
|
| 309 |
+
"eval_f1": 0.8946104799920928,
|
| 310 |
+
"eval_loss": 0.2225894331932068,
|
| 311 |
+
"eval_precision": 0.8872567105766707,
|
| 312 |
+
"eval_recall": 0.903381031095196,
|
| 313 |
+
"eval_runtime": 29.592,
|
| 314 |
+
"eval_samples_per_second": 255.948,
|
| 315 |
+
"eval_steps_per_second": 32.002,
|
| 316 |
+
"step": 17000
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"logging_steps": 1000,
|
| 320 |
+
"max_steps": 51273,
|
| 321 |
+
"num_input_tokens_seen": 0,
|
| 322 |
+
"num_train_epochs": 3,
|
| 323 |
+
"save_steps": 1000,
|
| 324 |
+
"stateful_callbacks": {
|
| 325 |
+
"TrainerControl": {
|
| 326 |
+
"args": {
|
| 327 |
+
"should_epoch_stop": false,
|
| 328 |
+
"should_evaluate": false,
|
| 329 |
+
"should_log": false,
|
| 330 |
+
"should_save": true,
|
| 331 |
+
"should_training_stop": false
|
| 332 |
+
},
|
| 333 |
+
"attributes": {}
|
| 334 |
+
}
|
| 335 |
+
},
|
| 336 |
+
"total_flos": 4442566947840000.0,
|
| 337 |
+
"train_batch_size": 8,
|
| 338 |
+
"trial_name": null,
|
| 339 |
+
"trial_params": null
|
| 340 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|