init v0.1.0
Browse files- config.json +50 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- trainer_state.json +373 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dbmdz/bert-base-german-uncased",
|
| 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": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Veranstalter",
|
| 13 |
+
"1": "Locations und R\u00e4ume",
|
| 14 |
+
"2": "Catering",
|
| 15 |
+
"3": "Agenturen",
|
| 16 |
+
"4": "Technik, B\u00fchnen- und Messebau",
|
| 17 |
+
"5": "Service",
|
| 18 |
+
"6": "Vermittler/Management",
|
| 19 |
+
"7": "Kreativ",
|
| 20 |
+
"8": "Entertainment",
|
| 21 |
+
"9": "Hersteller"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"Agenturen": 3,
|
| 27 |
+
"Catering": 2,
|
| 28 |
+
"Entertainment": 8,
|
| 29 |
+
"Hersteller": 9,
|
| 30 |
+
"Kreativ": 7,
|
| 31 |
+
"Locations und R\u00e4ume": 1,
|
| 32 |
+
"Service": 5,
|
| 33 |
+
"Technik, B\u00fchnen- und Messebau": 4,
|
| 34 |
+
"Veranstalter": 0,
|
| 35 |
+
"Vermittler/Management": 6
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"model_type": "bert",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_hidden_layers": 12,
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"position_embedding_type": "absolute",
|
| 44 |
+
"problem_type": "multi_label_classification",
|
| 45 |
+
"torch_dtype": "float32",
|
| 46 |
+
"transformers_version": "4.48.1",
|
| 47 |
+
"type_vocab_size": 2,
|
| 48 |
+
"use_cache": true,
|
| 49 |
+
"vocab_size": 31102
|
| 50 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8883c9b149c7c1232c658f95ac886b16bfd053f61f0e1f217519c57a606ad7a1
|
| 3 |
+
size 439765016
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e6eb439d7f202e934e4577034abd3cd7b7b49c77e34a7167988ec66eca4ce97
|
| 3 |
+
size 879645434
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0707f183779ce0b4728851dedd552186381f4c39ad995ad46d91f3818b27a4cc
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c1f92a1f7ef6ecdeac90c1d01e3e19d222e203c0577a3ecbde9adc6e28f111e
|
| 3 |
+
size 1064
|
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 |
+
}
|
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": "[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": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_len": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.15249475836753845,
|
| 3 |
+
"best_model_checkpoint": "/Users/davidbirkenberger/Documents/rifel_models/final/checkpoint-378",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 378,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.23809523809523808,
|
| 13 |
+
"grad_norm": 1.2485231161117554,
|
| 14 |
+
"learning_rate": 5.061503329725875e-05,
|
| 15 |
+
"loss": 0.4969,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.47619047619047616,
|
| 20 |
+
"grad_norm": 1.6543331146240234,
|
| 21 |
+
"learning_rate": 4.979866179246426e-05,
|
| 22 |
+
"loss": 0.4438,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7142857142857143,
|
| 27 |
+
"grad_norm": 1.400197148323059,
|
| 28 |
+
"learning_rate": 4.8982290287669756e-05,
|
| 29 |
+
"loss": 0.378,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9523809523809523,
|
| 34 |
+
"grad_norm": 1.311822533607483,
|
| 35 |
+
"learning_rate": 4.8165918782875265e-05,
|
| 36 |
+
"loss": 0.4147,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_loss": 0.3573644757270813,
|
| 42 |
+
"eval_runtime": 1.6061,
|
| 43 |
+
"eval_samples_per_second": 19.924,
|
| 44 |
+
"eval_steps_per_second": 6.849,
|
| 45 |
+
"step": 42
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.1904761904761905,
|
| 49 |
+
"grad_norm": 1.5031193494796753,
|
| 50 |
+
"learning_rate": 4.734954727808077e-05,
|
| 51 |
+
"loss": 0.337,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.4285714285714286,
|
| 56 |
+
"grad_norm": 1.6817210912704468,
|
| 57 |
+
"learning_rate": 4.6533175773286276e-05,
|
| 58 |
+
"loss": 0.3037,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.6666666666666665,
|
| 63 |
+
"grad_norm": 1.1621549129486084,
|
| 64 |
+
"learning_rate": 4.571680426849177e-05,
|
| 65 |
+
"loss": 0.3029,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.9047619047619047,
|
| 70 |
+
"grad_norm": 1.644331693649292,
|
| 71 |
+
"learning_rate": 4.490043276369728e-05,
|
| 72 |
+
"loss": 0.2911,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.0,
|
| 77 |
+
"eval_loss": 0.271997332572937,
|
| 78 |
+
"eval_runtime": 1.65,
|
| 79 |
+
"eval_samples_per_second": 19.394,
|
| 80 |
+
"eval_steps_per_second": 6.667,
|
| 81 |
+
"step": 84
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.142857142857143,
|
| 85 |
+
"grad_norm": 1.0107003450393677,
|
| 86 |
+
"learning_rate": 4.408406125890278e-05,
|
| 87 |
+
"loss": 0.2386,
|
| 88 |
+
"step": 90
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.380952380952381,
|
| 92 |
+
"grad_norm": 0.835885763168335,
|
| 93 |
+
"learning_rate": 4.326768975410829e-05,
|
| 94 |
+
"loss": 0.2218,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.619047619047619,
|
| 99 |
+
"grad_norm": 0.7079904079437256,
|
| 100 |
+
"learning_rate": 4.245131824931379e-05,
|
| 101 |
+
"loss": 0.2033,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.857142857142857,
|
| 106 |
+
"grad_norm": 1.4346115589141846,
|
| 107 |
+
"learning_rate": 4.16349467445193e-05,
|
| 108 |
+
"loss": 0.2206,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.0,
|
| 113 |
+
"eval_loss": 0.2123033106327057,
|
| 114 |
+
"eval_runtime": 1.5676,
|
| 115 |
+
"eval_samples_per_second": 20.414,
|
| 116 |
+
"eval_steps_per_second": 7.017,
|
| 117 |
+
"step": 126
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.0952380952380953,
|
| 121 |
+
"grad_norm": 1.273030400276184,
|
| 122 |
+
"learning_rate": 4.08185752397248e-05,
|
| 123 |
+
"loss": 0.1684,
|
| 124 |
+
"step": 130
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.3333333333333335,
|
| 128 |
+
"grad_norm": 0.7772669792175293,
|
| 129 |
+
"learning_rate": 4.000220373493031e-05,
|
| 130 |
+
"loss": 0.155,
|
| 131 |
+
"step": 140
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.571428571428571,
|
| 135 |
+
"grad_norm": 1.3734729290008545,
|
| 136 |
+
"learning_rate": 3.9185832230135803e-05,
|
| 137 |
+
"loss": 0.1655,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.8095238095238093,
|
| 142 |
+
"grad_norm": 1.454413652420044,
|
| 143 |
+
"learning_rate": 3.836946072534131e-05,
|
| 144 |
+
"loss": 0.1598,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.0,
|
| 149 |
+
"eval_loss": 0.2093825340270996,
|
| 150 |
+
"eval_runtime": 1.6719,
|
| 151 |
+
"eval_samples_per_second": 19.14,
|
| 152 |
+
"eval_steps_per_second": 6.579,
|
| 153 |
+
"step": 168
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.0476190476190474,
|
| 157 |
+
"grad_norm": 1.0927952527999878,
|
| 158 |
+
"learning_rate": 3.7553089220546815e-05,
|
| 159 |
+
"loss": 0.1394,
|
| 160 |
+
"step": 170
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 4.285714285714286,
|
| 164 |
+
"grad_norm": 1.0157573223114014,
|
| 165 |
+
"learning_rate": 3.6736717715752324e-05,
|
| 166 |
+
"loss": 0.1571,
|
| 167 |
+
"step": 180
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 4.523809523809524,
|
| 171 |
+
"grad_norm": 0.43212223052978516,
|
| 172 |
+
"learning_rate": 3.5920346210957826e-05,
|
| 173 |
+
"loss": 0.1281,
|
| 174 |
+
"step": 190
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.761904761904762,
|
| 178 |
+
"grad_norm": 0.6443906426429749,
|
| 179 |
+
"learning_rate": 3.510397470616333e-05,
|
| 180 |
+
"loss": 0.131,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.0,
|
| 185 |
+
"grad_norm": 1.5671747922897339,
|
| 186 |
+
"learning_rate": 3.428760320136883e-05,
|
| 187 |
+
"loss": 0.1466,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.0,
|
| 192 |
+
"eval_loss": 0.1823369264602661,
|
| 193 |
+
"eval_runtime": 1.6446,
|
| 194 |
+
"eval_samples_per_second": 19.458,
|
| 195 |
+
"eval_steps_per_second": 6.689,
|
| 196 |
+
"step": 210
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 5.238095238095238,
|
| 200 |
+
"grad_norm": 1.444640040397644,
|
| 201 |
+
"learning_rate": 3.347123169657434e-05,
|
| 202 |
+
"loss": 0.1252,
|
| 203 |
+
"step": 220
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.476190476190476,
|
| 207 |
+
"grad_norm": 1.4842709302902222,
|
| 208 |
+
"learning_rate": 3.265486019177984e-05,
|
| 209 |
+
"loss": 0.1176,
|
| 210 |
+
"step": 230
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 5.714285714285714,
|
| 214 |
+
"grad_norm": 1.338508129119873,
|
| 215 |
+
"learning_rate": 3.1838488686985344e-05,
|
| 216 |
+
"loss": 0.1013,
|
| 217 |
+
"step": 240
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 5.9523809523809526,
|
| 221 |
+
"grad_norm": 0.5218590497970581,
|
| 222 |
+
"learning_rate": 3.1022117182190846e-05,
|
| 223 |
+
"loss": 0.0871,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.0,
|
| 228 |
+
"eval_loss": 0.16389165818691254,
|
| 229 |
+
"eval_runtime": 1.7452,
|
| 230 |
+
"eval_samples_per_second": 18.336,
|
| 231 |
+
"eval_steps_per_second": 6.303,
|
| 232 |
+
"step": 252
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 6.190476190476191,
|
| 236 |
+
"grad_norm": 1.4809467792510986,
|
| 237 |
+
"learning_rate": 3.0205745677396355e-05,
|
| 238 |
+
"loss": 0.1164,
|
| 239 |
+
"step": 260
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.428571428571429,
|
| 243 |
+
"grad_norm": 0.4164857566356659,
|
| 244 |
+
"learning_rate": 2.9389374172601854e-05,
|
| 245 |
+
"loss": 0.074,
|
| 246 |
+
"step": 270
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 6.666666666666667,
|
| 250 |
+
"grad_norm": 0.37571170926094055,
|
| 251 |
+
"learning_rate": 2.8573002667807363e-05,
|
| 252 |
+
"loss": 0.0815,
|
| 253 |
+
"step": 280
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 6.904761904761905,
|
| 257 |
+
"grad_norm": 1.2223498821258545,
|
| 258 |
+
"learning_rate": 2.7756631163012862e-05,
|
| 259 |
+
"loss": 0.088,
|
| 260 |
+
"step": 290
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 7.0,
|
| 264 |
+
"eval_loss": 0.15850776433944702,
|
| 265 |
+
"eval_runtime": 1.5802,
|
| 266 |
+
"eval_samples_per_second": 20.251,
|
| 267 |
+
"eval_steps_per_second": 6.961,
|
| 268 |
+
"step": 294
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.142857142857143,
|
| 272 |
+
"grad_norm": 1.3939220905303955,
|
| 273 |
+
"learning_rate": 2.694025965821837e-05,
|
| 274 |
+
"loss": 0.1117,
|
| 275 |
+
"step": 300
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.380952380952381,
|
| 279 |
+
"grad_norm": 0.8872294425964355,
|
| 280 |
+
"learning_rate": 2.612388815342387e-05,
|
| 281 |
+
"loss": 0.0748,
|
| 282 |
+
"step": 310
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.619047619047619,
|
| 286 |
+
"grad_norm": 0.7376847267150879,
|
| 287 |
+
"learning_rate": 2.5307516648629376e-05,
|
| 288 |
+
"loss": 0.0768,
|
| 289 |
+
"step": 320
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.857142857142857,
|
| 293 |
+
"grad_norm": 1.4566947221755981,
|
| 294 |
+
"learning_rate": 2.4491145143834878e-05,
|
| 295 |
+
"loss": 0.0675,
|
| 296 |
+
"step": 330
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.0,
|
| 300 |
+
"eval_loss": 0.16645725071430206,
|
| 301 |
+
"eval_runtime": 1.6616,
|
| 302 |
+
"eval_samples_per_second": 19.258,
|
| 303 |
+
"eval_steps_per_second": 6.62,
|
| 304 |
+
"step": 336
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 8.095238095238095,
|
| 308 |
+
"grad_norm": 0.39620542526245117,
|
| 309 |
+
"learning_rate": 2.3674773639040384e-05,
|
| 310 |
+
"loss": 0.0763,
|
| 311 |
+
"step": 340
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 8.333333333333334,
|
| 315 |
+
"grad_norm": 0.24305318295955658,
|
| 316 |
+
"learning_rate": 2.2858402134245886e-05,
|
| 317 |
+
"loss": 0.052,
|
| 318 |
+
"step": 350
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 8.571428571428571,
|
| 322 |
+
"grad_norm": 0.3784918487071991,
|
| 323 |
+
"learning_rate": 2.204203062945139e-05,
|
| 324 |
+
"loss": 0.0625,
|
| 325 |
+
"step": 360
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 8.80952380952381,
|
| 329 |
+
"grad_norm": 0.25161460041999817,
|
| 330 |
+
"learning_rate": 2.1225659124656894e-05,
|
| 331 |
+
"loss": 0.0673,
|
| 332 |
+
"step": 370
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 9.0,
|
| 336 |
+
"eval_loss": 0.15249475836753845,
|
| 337 |
+
"eval_runtime": 1.6247,
|
| 338 |
+
"eval_samples_per_second": 19.697,
|
| 339 |
+
"eval_steps_per_second": 6.771,
|
| 340 |
+
"step": 378
|
| 341 |
+
}
|
| 342 |
+
],
|
| 343 |
+
"logging_steps": 10,
|
| 344 |
+
"max_steps": 630,
|
| 345 |
+
"num_input_tokens_seen": 0,
|
| 346 |
+
"num_train_epochs": 15,
|
| 347 |
+
"save_steps": 500,
|
| 348 |
+
"stateful_callbacks": {
|
| 349 |
+
"EarlyStoppingCallback": {
|
| 350 |
+
"args": {
|
| 351 |
+
"early_stopping_patience": 2,
|
| 352 |
+
"early_stopping_threshold": 0.001
|
| 353 |
+
},
|
| 354 |
+
"attributes": {
|
| 355 |
+
"early_stopping_patience_counter": 0
|
| 356 |
+
}
|
| 357 |
+
},
|
| 358 |
+
"TrainerControl": {
|
| 359 |
+
"args": {
|
| 360 |
+
"should_epoch_stop": false,
|
| 361 |
+
"should_evaluate": false,
|
| 362 |
+
"should_log": false,
|
| 363 |
+
"should_save": true,
|
| 364 |
+
"should_training_stop": false
|
| 365 |
+
},
|
| 366 |
+
"attributes": {}
|
| 367 |
+
}
|
| 368 |
+
},
|
| 369 |
+
"total_flos": 280687197719796.0,
|
| 370 |
+
"train_batch_size": 3,
|
| 371 |
+
"trial_name": null,
|
| 372 |
+
"trial_params": null
|
| 373 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74ad860000cf3d2d3d7e6134d4cb56650a0fe73fb2b8c2c45d1cac71b630f465
|
| 3 |
+
size 5432
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|