Upload 11 files
Browse files- config.json +35 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +262 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/hpcwork/vg380347/EduGBERT/encoder_model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 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": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-SKILL",
|
| 14 |
+
"2": "I-SKILL"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"B-SKILL": 1,
|
| 20 |
+
"I-SKILL": 2,
|
| 21 |
+
"O": 0
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.34.1",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 31102
|
| 35 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c257e5b373b0b939801e338458560e991c838acc0612c4e84160446dac004ad
|
| 3 |
+
size 2677841447
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88460ba7ed2c2f0ef0fdfd341fe4eb1a6fc0b1629cef1a37caf588b55daeb253
|
| 3 |
+
size 1338891366
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08bf259494a2f35595ce33d3a55ab19efcea58525bf1d09b2b2f5c377d85b98c
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3cdfafc9d216f4d90f4030c693dc2b96ea4dbac55bced425e04c263f0e60a49
|
| 3 |
+
size 1064
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"101": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"102": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"103": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 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": false,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_len": 512,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": false,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.21624045073986053,
|
| 3 |
+
"best_model_checkpoint": "/hpcwork/vg380347/NER/EduGBERT/checkpoint-550",
|
| 4 |
+
"epoch": 7.446808510638298,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1050,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.35,
|
| 13 |
+
"eval_f1": 0.5815712900096993,
|
| 14 |
+
"eval_loss": 0.3045153319835663,
|
| 15 |
+
"eval_precision": 0.5216332212040367,
|
| 16 |
+
"eval_recall": 0.6570718877849211,
|
| 17 |
+
"eval_runtime": 7.1562,
|
| 18 |
+
"eval_samples_per_second": 629.381,
|
| 19 |
+
"eval_steps_per_second": 5.031,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.71,
|
| 24 |
+
"eval_f1": 0.6822522225880804,
|
| 25 |
+
"eval_loss": 0.25079214572906494,
|
| 26 |
+
"eval_precision": 0.6210286536386525,
|
| 27 |
+
"eval_recall": 0.7568673290473408,
|
| 28 |
+
"eval_runtime": 7.2954,
|
| 29 |
+
"eval_samples_per_second": 617.376,
|
| 30 |
+
"eval_steps_per_second": 4.935,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.06,
|
| 35 |
+
"eval_f1": 0.7016087182148418,
|
| 36 |
+
"eval_loss": 0.24814821779727936,
|
| 37 |
+
"eval_precision": 0.6308912739150724,
|
| 38 |
+
"eval_recall": 0.7901811805961426,
|
| 39 |
+
"eval_runtime": 7.1783,
|
| 40 |
+
"eval_samples_per_second": 627.45,
|
| 41 |
+
"eval_steps_per_second": 5.015,
|
| 42 |
+
"step": 150
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.42,
|
| 46 |
+
"eval_f1": 0.7199271355149306,
|
| 47 |
+
"eval_loss": 0.2445540428161621,
|
| 48 |
+
"eval_precision": 0.6488800281458895,
|
| 49 |
+
"eval_recall": 0.8084453535943893,
|
| 50 |
+
"eval_runtime": 7.1384,
|
| 51 |
+
"eval_samples_per_second": 630.95,
|
| 52 |
+
"eval_steps_per_second": 5.043,
|
| 53 |
+
"step": 200
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.77,
|
| 57 |
+
"eval_f1": 0.722252082773448,
|
| 58 |
+
"eval_loss": 0.22964715957641602,
|
| 59 |
+
"eval_precision": 0.6685323383084577,
|
| 60 |
+
"eval_recall": 0.7853594389246055,
|
| 61 |
+
"eval_runtime": 7.434,
|
| 62 |
+
"eval_samples_per_second": 605.866,
|
| 63 |
+
"eval_steps_per_second": 4.843,
|
| 64 |
+
"step": 250
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.13,
|
| 68 |
+
"eval_f1": 0.7319960997353392,
|
| 69 |
+
"eval_loss": 0.21758420765399933,
|
| 70 |
+
"eval_precision": 0.6993611924407772,
|
| 71 |
+
"eval_recall": 0.7678258328462887,
|
| 72 |
+
"eval_runtime": 7.1469,
|
| 73 |
+
"eval_samples_per_second": 630.207,
|
| 74 |
+
"eval_steps_per_second": 5.037,
|
| 75 |
+
"step": 300
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.48,
|
| 79 |
+
"eval_f1": 0.7406113537117905,
|
| 80 |
+
"eval_loss": 0.22185301780700684,
|
| 81 |
+
"eval_precision": 0.6854868797413257,
|
| 82 |
+
"eval_recall": 0.8053769725306839,
|
| 83 |
+
"eval_runtime": 7.1574,
|
| 84 |
+
"eval_samples_per_second": 629.281,
|
| 85 |
+
"eval_steps_per_second": 5.03,
|
| 86 |
+
"step": 350
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.84,
|
| 90 |
+
"eval_f1": 0.7412340309866812,
|
| 91 |
+
"eval_loss": 0.2164618819952011,
|
| 92 |
+
"eval_precision": 0.6928353658536586,
|
| 93 |
+
"eval_recall": 0.7969023962594973,
|
| 94 |
+
"eval_runtime": 7.1409,
|
| 95 |
+
"eval_samples_per_second": 630.735,
|
| 96 |
+
"eval_steps_per_second": 5.041,
|
| 97 |
+
"step": 400
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 3.19,
|
| 101 |
+
"eval_f1": 0.7499483221938952,
|
| 102 |
+
"eval_loss": 0.2220638245344162,
|
| 103 |
+
"eval_precision": 0.7096101186595384,
|
| 104 |
+
"eval_recall": 0.7951490356516657,
|
| 105 |
+
"eval_runtime": 7.4483,
|
| 106 |
+
"eval_samples_per_second": 604.703,
|
| 107 |
+
"eval_steps_per_second": 4.833,
|
| 108 |
+
"step": 450
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.55,
|
| 112 |
+
"learning_rate": 4.822695035460993e-06,
|
| 113 |
+
"loss": 0.2581,
|
| 114 |
+
"step": 500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.55,
|
| 118 |
+
"eval_f1": 0.7439247452312516,
|
| 119 |
+
"eval_loss": 0.2487693727016449,
|
| 120 |
+
"eval_precision": 0.6727315689981096,
|
| 121 |
+
"eval_recall": 0.8319696084161309,
|
| 122 |
+
"eval_runtime": 7.1497,
|
| 123 |
+
"eval_samples_per_second": 629.957,
|
| 124 |
+
"eval_steps_per_second": 5.035,
|
| 125 |
+
"step": 500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.9,
|
| 129 |
+
"eval_f1": 0.7555155958226711,
|
| 130 |
+
"eval_loss": 0.21624045073986053,
|
| 131 |
+
"eval_precision": 0.717268548916612,
|
| 132 |
+
"eval_recall": 0.7980713033313852,
|
| 133 |
+
"eval_runtime": 7.1536,
|
| 134 |
+
"eval_samples_per_second": 629.612,
|
| 135 |
+
"eval_steps_per_second": 5.032,
|
| 136 |
+
"step": 550
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.26,
|
| 140 |
+
"eval_f1": 0.7588671611598112,
|
| 141 |
+
"eval_loss": 0.23951853811740875,
|
| 142 |
+
"eval_precision": 0.7046080641121963,
|
| 143 |
+
"eval_recall": 0.8221800116890707,
|
| 144 |
+
"eval_runtime": 7.0397,
|
| 145 |
+
"eval_samples_per_second": 639.8,
|
| 146 |
+
"eval_steps_per_second": 5.114,
|
| 147 |
+
"step": 600
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.61,
|
| 151 |
+
"eval_f1": 0.7562726374711887,
|
| 152 |
+
"eval_loss": 0.24661774933338165,
|
| 153 |
+
"eval_precision": 0.688406665867402,
|
| 154 |
+
"eval_recall": 0.8389830508474576,
|
| 155 |
+
"eval_runtime": 7.1388,
|
| 156 |
+
"eval_samples_per_second": 630.916,
|
| 157 |
+
"eval_steps_per_second": 5.043,
|
| 158 |
+
"step": 650
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.96,
|
| 162 |
+
"eval_f1": 0.7577822311289245,
|
| 163 |
+
"eval_loss": 0.24025806784629822,
|
| 164 |
+
"eval_precision": 0.6980063992124046,
|
| 165 |
+
"eval_recall": 0.8287551139684395,
|
| 166 |
+
"eval_runtime": 7.1329,
|
| 167 |
+
"eval_samples_per_second": 631.441,
|
| 168 |
+
"eval_steps_per_second": 5.047,
|
| 169 |
+
"step": 700
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 5.32,
|
| 173 |
+
"eval_f1": 0.7517815517815518,
|
| 174 |
+
"eval_loss": 0.261866956949234,
|
| 175 |
+
"eval_precision": 0.6907355280871375,
|
| 176 |
+
"eval_recall": 0.8246639392168322,
|
| 177 |
+
"eval_runtime": 7.3254,
|
| 178 |
+
"eval_samples_per_second": 614.846,
|
| 179 |
+
"eval_steps_per_second": 4.914,
|
| 180 |
+
"step": 750
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.67,
|
| 184 |
+
"eval_f1": 0.7615306467998646,
|
| 185 |
+
"eval_loss": 0.2429821491241455,
|
| 186 |
+
"eval_precision": 0.7097588688296932,
|
| 187 |
+
"eval_recall": 0.8214494447691408,
|
| 188 |
+
"eval_runtime": 7.1352,
|
| 189 |
+
"eval_samples_per_second": 631.236,
|
| 190 |
+
"eval_steps_per_second": 5.045,
|
| 191 |
+
"step": 800
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.03,
|
| 195 |
+
"eval_f1": 0.7594460131773565,
|
| 196 |
+
"eval_loss": 0.24021703004837036,
|
| 197 |
+
"eval_precision": 0.7033623910336239,
|
| 198 |
+
"eval_recall": 0.8252483927527762,
|
| 199 |
+
"eval_runtime": 7.155,
|
| 200 |
+
"eval_samples_per_second": 629.489,
|
| 201 |
+
"eval_steps_per_second": 5.031,
|
| 202 |
+
"step": 850
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.38,
|
| 206 |
+
"eval_f1": 0.7594716019580233,
|
| 207 |
+
"eval_loss": 0.25845229625701904,
|
| 208 |
+
"eval_precision": 0.70182178708638,
|
| 209 |
+
"eval_recall": 0.8274400935125658,
|
| 210 |
+
"eval_runtime": 7.1743,
|
| 211 |
+
"eval_samples_per_second": 627.796,
|
| 212 |
+
"eval_steps_per_second": 5.018,
|
| 213 |
+
"step": 900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.74,
|
| 217 |
+
"eval_f1": 0.7634940255459416,
|
| 218 |
+
"eval_loss": 0.2463415563106537,
|
| 219 |
+
"eval_precision": 0.7202643171806168,
|
| 220 |
+
"eval_recall": 0.8122443015780245,
|
| 221 |
+
"eval_runtime": 7.1315,
|
| 222 |
+
"eval_samples_per_second": 631.568,
|
| 223 |
+
"eval_steps_per_second": 5.048,
|
| 224 |
+
"step": 950
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.09,
|
| 228 |
+
"learning_rate": 4.645390070921986e-06,
|
| 229 |
+
"loss": 0.1517,
|
| 230 |
+
"step": 1000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.09,
|
| 234 |
+
"eval_f1": 0.7641669494401085,
|
| 235 |
+
"eval_loss": 0.25761693716049194,
|
| 236 |
+
"eval_precision": 0.7134710429603346,
|
| 237 |
+
"eval_recall": 0.8226183518410286,
|
| 238 |
+
"eval_runtime": 7.1379,
|
| 239 |
+
"eval_samples_per_second": 630.995,
|
| 240 |
+
"eval_steps_per_second": 5.043,
|
| 241 |
+
"step": 1000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 7.45,
|
| 245 |
+
"eval_f1": 0.7703476197124111,
|
| 246 |
+
"eval_loss": 0.2536332607269287,
|
| 247 |
+
"eval_precision": 0.7375033413525796,
|
| 248 |
+
"eval_recall": 0.8062536528345996,
|
| 249 |
+
"eval_runtime": 7.1375,
|
| 250 |
+
"eval_samples_per_second": 631.035,
|
| 251 |
+
"eval_steps_per_second": 5.044,
|
| 252 |
+
"step": 1050
|
| 253 |
+
}
|
| 254 |
+
],
|
| 255 |
+
"logging_steps": 500,
|
| 256 |
+
"max_steps": 14100,
|
| 257 |
+
"num_train_epochs": 100,
|
| 258 |
+
"save_steps": 50,
|
| 259 |
+
"total_flos": 6.408198647855674e+16,
|
| 260 |
+
"trial_name": null,
|
| 261 |
+
"trial_params": null
|
| 262 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:010261ff7075e337d4172e334ca45bf6f468f628bfc9d5e82aac3a37fdfad0c8
|
| 3 |
+
size 4536
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|