Shu Huang
commited on
Commit
·
2f80444
1
Parent(s):
c2e0936
cner
Browse files- all_results.json +17 -0
- config.json +37 -0
- eval_results.json +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +1369 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.9971162069527343,
|
| 4 |
+
"eval_f1": 0.960166445260608,
|
| 5 |
+
"eval_loss": 0.03031528927385807,
|
| 6 |
+
"eval_precision": 0.9533868715083799,
|
| 7 |
+
"eval_recall": 0.9670431292302849,
|
| 8 |
+
"eval_runtime": 49.5331,
|
| 9 |
+
"eval_samples": 22230,
|
| 10 |
+
"eval_samples_per_second": 448.791,
|
| 11 |
+
"eval_steps_per_second": 28.062,
|
| 12 |
+
"train_loss": 0.0005194992909466218,
|
| 13 |
+
"train_runtime": 2998.8244,
|
| 14 |
+
"train_samples": 103879,
|
| 15 |
+
"train_samples_per_second": 519.599,
|
| 16 |
+
"train_steps_per_second": 32.478
|
| 17 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/lus/theta-fs0/projects/SolarWindowsADSP/shu/models/best_models/bert/batterybert-cased/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"finetuning_task": "ner",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-MAT",
|
| 15 |
+
"1": "I-MAT",
|
| 16 |
+
"2": "O"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"B-MAT": 0,
|
| 22 |
+
"I-MAT": 1,
|
| 23 |
+
"O": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.18.0.dev0",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 28996
|
| 37 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.9971162069527343,
|
| 4 |
+
"eval_f1": 0.960166445260608,
|
| 5 |
+
"eval_loss": 0.03031528927385807,
|
| 6 |
+
"eval_precision": 0.9533868715083799,
|
| 7 |
+
"eval_recall": 0.9670431292302849,
|
| 8 |
+
"eval_runtime": 49.5331,
|
| 9 |
+
"eval_samples": 22230,
|
| 10 |
+
"eval_samples_per_second": 448.791,
|
| 11 |
+
"eval_steps_per_second": 28.062
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b2a648f4c0a880d1a9cbfb75b64f87b42bdffcc6b5e0047386dee8cbc2099f4
|
| 3 |
+
size 430972273
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/lus/theta-fs0/projects/SolarWindowsADSP/shu/models/best_models/bert/batterybert-cased/", "tokenizer_class": "BertTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_loss": 0.0005194992909466218,
|
| 4 |
+
"train_runtime": 2998.8244,
|
| 5 |
+
"train_samples": 103879,
|
| 6 |
+
"train_samples_per_second": 519.599,
|
| 7 |
+
"train_steps_per_second": 32.478
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"global_step": 97395,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 1.9897325324708663e-05,
|
| 13 |
+
"loss": 0.0654,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.15,
|
| 18 |
+
"learning_rate": 1.9794650649417323e-05,
|
| 19 |
+
"loss": 0.0404,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.23,
|
| 24 |
+
"learning_rate": 1.9691975974125984e-05,
|
| 25 |
+
"loss": 0.0376,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.31,
|
| 30 |
+
"learning_rate": 1.9589301298834645e-05,
|
| 31 |
+
"loss": 0.0326,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.39,
|
| 36 |
+
"learning_rate": 1.9486626623543306e-05,
|
| 37 |
+
"loss": 0.0339,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.46,
|
| 42 |
+
"learning_rate": 1.9383951948251964e-05,
|
| 43 |
+
"loss": 0.0308,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"learning_rate": 1.9281277272960624e-05,
|
| 49 |
+
"loss": 0.0286,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.62,
|
| 54 |
+
"learning_rate": 1.9178602597669285e-05,
|
| 55 |
+
"loss": 0.0288,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.69,
|
| 60 |
+
"learning_rate": 1.907592792237795e-05,
|
| 61 |
+
"loss": 0.0297,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.77,
|
| 66 |
+
"learning_rate": 1.8973253247086607e-05,
|
| 67 |
+
"loss": 0.0265,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.85,
|
| 72 |
+
"learning_rate": 1.8870578571795268e-05,
|
| 73 |
+
"loss": 0.0268,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.92,
|
| 78 |
+
"learning_rate": 1.876790389650393e-05,
|
| 79 |
+
"loss": 0.026,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_accuracy": 0.9921017969396702,
|
| 85 |
+
"eval_f1": 0.8958375556134611,
|
| 86 |
+
"eval_loss": 0.02251129411160946,
|
| 87 |
+
"eval_precision": 0.8791317030666944,
|
| 88 |
+
"eval_recall": 0.9131906186053833,
|
| 89 |
+
"eval_runtime": 49.8627,
|
| 90 |
+
"eval_samples_per_second": 445.824,
|
| 91 |
+
"eval_steps_per_second": 27.877,
|
| 92 |
+
"step": 6493
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.0,
|
| 96 |
+
"learning_rate": 1.866522922121259e-05,
|
| 97 |
+
"loss": 0.0267,
|
| 98 |
+
"step": 6500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.08,
|
| 102 |
+
"learning_rate": 1.856255454592125e-05,
|
| 103 |
+
"loss": 0.0187,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.16,
|
| 108 |
+
"learning_rate": 1.845987987062991e-05,
|
| 109 |
+
"loss": 0.0192,
|
| 110 |
+
"step": 7500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.23,
|
| 114 |
+
"learning_rate": 1.8357205195338572e-05,
|
| 115 |
+
"loss": 0.0184,
|
| 116 |
+
"step": 8000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.31,
|
| 120 |
+
"learning_rate": 1.825453052004723e-05,
|
| 121 |
+
"loss": 0.0185,
|
| 122 |
+
"step": 8500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.39,
|
| 126 |
+
"learning_rate": 1.8151855844755894e-05,
|
| 127 |
+
"loss": 0.0184,
|
| 128 |
+
"step": 9000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.46,
|
| 132 |
+
"learning_rate": 1.8049181169464555e-05,
|
| 133 |
+
"loss": 0.0186,
|
| 134 |
+
"step": 9500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.54,
|
| 138 |
+
"learning_rate": 1.7946506494173212e-05,
|
| 139 |
+
"loss": 0.0188,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.62,
|
| 144 |
+
"learning_rate": 1.7843831818881873e-05,
|
| 145 |
+
"loss": 0.0175,
|
| 146 |
+
"step": 10500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.69,
|
| 150 |
+
"learning_rate": 1.7741157143590534e-05,
|
| 151 |
+
"loss": 0.0182,
|
| 152 |
+
"step": 11000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.77,
|
| 156 |
+
"learning_rate": 1.7638482468299195e-05,
|
| 157 |
+
"loss": 0.0186,
|
| 158 |
+
"step": 11500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.85,
|
| 162 |
+
"learning_rate": 1.7535807793007856e-05,
|
| 163 |
+
"loss": 0.0171,
|
| 164 |
+
"step": 12000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.93,
|
| 168 |
+
"learning_rate": 1.7433133117716517e-05,
|
| 169 |
+
"loss": 0.0175,
|
| 170 |
+
"step": 12500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.0,
|
| 174 |
+
"eval_accuracy": 0.9928925721440631,
|
| 175 |
+
"eval_f1": 0.9121865334285035,
|
| 176 |
+
"eval_loss": 0.022899635136127472,
|
| 177 |
+
"eval_precision": 0.8833754216512139,
|
| 178 |
+
"eval_recall": 0.9429403431449709,
|
| 179 |
+
"eval_runtime": 50.1306,
|
| 180 |
+
"eval_samples_per_second": 443.442,
|
| 181 |
+
"eval_steps_per_second": 27.728,
|
| 182 |
+
"step": 12986
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.0,
|
| 186 |
+
"learning_rate": 1.7330458442425178e-05,
|
| 187 |
+
"loss": 0.0174,
|
| 188 |
+
"step": 13000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.08,
|
| 192 |
+
"learning_rate": 1.722778376713384e-05,
|
| 193 |
+
"loss": 0.0112,
|
| 194 |
+
"step": 13500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.16,
|
| 198 |
+
"learning_rate": 1.71251090918425e-05,
|
| 199 |
+
"loss": 0.0119,
|
| 200 |
+
"step": 14000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.23,
|
| 204 |
+
"learning_rate": 1.702243441655116e-05,
|
| 205 |
+
"loss": 0.011,
|
| 206 |
+
"step": 14500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.31,
|
| 210 |
+
"learning_rate": 1.691975974125982e-05,
|
| 211 |
+
"loss": 0.0128,
|
| 212 |
+
"step": 15000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.39,
|
| 216 |
+
"learning_rate": 1.681708506596848e-05,
|
| 217 |
+
"loss": 0.0115,
|
| 218 |
+
"step": 15500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.46,
|
| 222 |
+
"learning_rate": 1.671441039067714e-05,
|
| 223 |
+
"loss": 0.0119,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.54,
|
| 228 |
+
"learning_rate": 1.66117357153858e-05,
|
| 229 |
+
"loss": 0.0121,
|
| 230 |
+
"step": 16500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.62,
|
| 234 |
+
"learning_rate": 1.650906104009446e-05,
|
| 235 |
+
"loss": 0.0129,
|
| 236 |
+
"step": 17000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.7,
|
| 240 |
+
"learning_rate": 1.6406386364803122e-05,
|
| 241 |
+
"loss": 0.0122,
|
| 242 |
+
"step": 17500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.77,
|
| 246 |
+
"learning_rate": 1.6303711689511783e-05,
|
| 247 |
+
"loss": 0.0119,
|
| 248 |
+
"step": 18000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.85,
|
| 252 |
+
"learning_rate": 1.6201037014220444e-05,
|
| 253 |
+
"loss": 0.0113,
|
| 254 |
+
"step": 18500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.93,
|
| 258 |
+
"learning_rate": 1.6098362338929105e-05,
|
| 259 |
+
"loss": 0.0123,
|
| 260 |
+
"step": 19000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0,
|
| 264 |
+
"eval_accuracy": 0.994509334429875,
|
| 265 |
+
"eval_f1": 0.9276342822196103,
|
| 266 |
+
"eval_loss": 0.018586399033665657,
|
| 267 |
+
"eval_precision": 0.9017742684626103,
|
| 268 |
+
"eval_recall": 0.9550212498032425,
|
| 269 |
+
"eval_runtime": 49.8184,
|
| 270 |
+
"eval_samples_per_second": 446.221,
|
| 271 |
+
"eval_steps_per_second": 27.901,
|
| 272 |
+
"step": 19479
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.0,
|
| 276 |
+
"learning_rate": 1.5995687663637766e-05,
|
| 277 |
+
"loss": 0.0114,
|
| 278 |
+
"step": 19500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.08,
|
| 282 |
+
"learning_rate": 1.5893012988346427e-05,
|
| 283 |
+
"loss": 0.0079,
|
| 284 |
+
"step": 20000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.16,
|
| 288 |
+
"learning_rate": 1.5790338313055087e-05,
|
| 289 |
+
"loss": 0.0089,
|
| 290 |
+
"step": 20500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.23,
|
| 294 |
+
"learning_rate": 1.5687663637763745e-05,
|
| 295 |
+
"loss": 0.0082,
|
| 296 |
+
"step": 21000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.31,
|
| 300 |
+
"learning_rate": 1.5584988962472406e-05,
|
| 301 |
+
"loss": 0.0079,
|
| 302 |
+
"step": 21500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.39,
|
| 306 |
+
"learning_rate": 1.5482314287181067e-05,
|
| 307 |
+
"loss": 0.0091,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.47,
|
| 312 |
+
"learning_rate": 1.537963961188973e-05,
|
| 313 |
+
"loss": 0.0077,
|
| 314 |
+
"step": 22500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.54,
|
| 318 |
+
"learning_rate": 1.527696493659839e-05,
|
| 319 |
+
"loss": 0.0092,
|
| 320 |
+
"step": 23000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.62,
|
| 324 |
+
"learning_rate": 1.517429026130705e-05,
|
| 325 |
+
"loss": 0.0085,
|
| 326 |
+
"step": 23500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.7,
|
| 330 |
+
"learning_rate": 1.507161558601571e-05,
|
| 331 |
+
"loss": 0.008,
|
| 332 |
+
"step": 24000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.77,
|
| 336 |
+
"learning_rate": 1.4968940910724373e-05,
|
| 337 |
+
"loss": 0.0086,
|
| 338 |
+
"step": 24500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.85,
|
| 342 |
+
"learning_rate": 1.4866266235433032e-05,
|
| 343 |
+
"loss": 0.0073,
|
| 344 |
+
"step": 25000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.93,
|
| 348 |
+
"learning_rate": 1.4763591560141693e-05,
|
| 349 |
+
"loss": 0.008,
|
| 350 |
+
"step": 25500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.0,
|
| 354 |
+
"eval_accuracy": 0.9950017038967611,
|
| 355 |
+
"eval_f1": 0.9330951266348846,
|
| 356 |
+
"eval_loss": 0.018245086073875427,
|
| 357 |
+
"eval_precision": 0.9069028915259904,
|
| 358 |
+
"eval_recall": 0.9608452699512041,
|
| 359 |
+
"eval_runtime": 50.0297,
|
| 360 |
+
"eval_samples_per_second": 444.336,
|
| 361 |
+
"eval_steps_per_second": 27.783,
|
| 362 |
+
"step": 25972
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.0,
|
| 366 |
+
"learning_rate": 1.4660916884850354e-05,
|
| 367 |
+
"loss": 0.0093,
|
| 368 |
+
"step": 26000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.08,
|
| 372 |
+
"learning_rate": 1.4558242209559013e-05,
|
| 373 |
+
"loss": 0.0052,
|
| 374 |
+
"step": 26500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.16,
|
| 378 |
+
"learning_rate": 1.4455567534267674e-05,
|
| 379 |
+
"loss": 0.006,
|
| 380 |
+
"step": 27000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.24,
|
| 384 |
+
"learning_rate": 1.4352892858976335e-05,
|
| 385 |
+
"loss": 0.0056,
|
| 386 |
+
"step": 27500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.31,
|
| 390 |
+
"learning_rate": 1.4250218183684995e-05,
|
| 391 |
+
"loss": 0.0057,
|
| 392 |
+
"step": 28000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.39,
|
| 396 |
+
"learning_rate": 1.4147543508393655e-05,
|
| 397 |
+
"loss": 0.0059,
|
| 398 |
+
"step": 28500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.47,
|
| 402 |
+
"learning_rate": 1.4044868833102317e-05,
|
| 403 |
+
"loss": 0.0053,
|
| 404 |
+
"step": 29000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.54,
|
| 408 |
+
"learning_rate": 1.3942194157810978e-05,
|
| 409 |
+
"loss": 0.0062,
|
| 410 |
+
"step": 29500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.62,
|
| 414 |
+
"learning_rate": 1.3839519482519637e-05,
|
| 415 |
+
"loss": 0.006,
|
| 416 |
+
"step": 30000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.7,
|
| 420 |
+
"learning_rate": 1.3736844807228298e-05,
|
| 421 |
+
"loss": 0.0066,
|
| 422 |
+
"step": 30500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.77,
|
| 426 |
+
"learning_rate": 1.3634170131936959e-05,
|
| 427 |
+
"loss": 0.0061,
|
| 428 |
+
"step": 31000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.85,
|
| 432 |
+
"learning_rate": 1.353149545664562e-05,
|
| 433 |
+
"loss": 0.0062,
|
| 434 |
+
"step": 31500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.93,
|
| 438 |
+
"learning_rate": 1.3428820781354279e-05,
|
| 439 |
+
"loss": 0.0054,
|
| 440 |
+
"step": 32000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.0,
|
| 444 |
+
"eval_accuracy": 0.9954946701751224,
|
| 445 |
+
"eval_f1": 0.9372088797069429,
|
| 446 |
+
"eval_loss": 0.01748497784137726,
|
| 447 |
+
"eval_precision": 0.911872545552681,
|
| 448 |
+
"eval_recall": 0.9639933889501023,
|
| 449 |
+
"eval_runtime": 49.8931,
|
| 450 |
+
"eval_samples_per_second": 445.553,
|
| 451 |
+
"eval_steps_per_second": 27.86,
|
| 452 |
+
"step": 32465
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.01,
|
| 456 |
+
"learning_rate": 1.332614610606294e-05,
|
| 457 |
+
"loss": 0.0056,
|
| 458 |
+
"step": 32500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.08,
|
| 462 |
+
"learning_rate": 1.3223471430771601e-05,
|
| 463 |
+
"loss": 0.0038,
|
| 464 |
+
"step": 33000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.16,
|
| 468 |
+
"learning_rate": 1.3120796755480263e-05,
|
| 469 |
+
"loss": 0.0041,
|
| 470 |
+
"step": 33500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.24,
|
| 474 |
+
"learning_rate": 1.3018122080188923e-05,
|
| 475 |
+
"loss": 0.0039,
|
| 476 |
+
"step": 34000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.31,
|
| 480 |
+
"learning_rate": 1.2915447404897584e-05,
|
| 481 |
+
"loss": 0.0045,
|
| 482 |
+
"step": 34500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.39,
|
| 486 |
+
"learning_rate": 1.2812772729606244e-05,
|
| 487 |
+
"loss": 0.0058,
|
| 488 |
+
"step": 35000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.47,
|
| 492 |
+
"learning_rate": 1.2710098054314904e-05,
|
| 493 |
+
"loss": 0.0045,
|
| 494 |
+
"step": 35500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.54,
|
| 498 |
+
"learning_rate": 1.2607423379023564e-05,
|
| 499 |
+
"loss": 0.005,
|
| 500 |
+
"step": 36000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.62,
|
| 504 |
+
"learning_rate": 1.2504748703732225e-05,
|
| 505 |
+
"loss": 0.004,
|
| 506 |
+
"step": 36500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.7,
|
| 510 |
+
"learning_rate": 1.2402074028440886e-05,
|
| 511 |
+
"loss": 0.0047,
|
| 512 |
+
"step": 37000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.78,
|
| 516 |
+
"learning_rate": 1.2299399353149545e-05,
|
| 517 |
+
"loss": 0.0043,
|
| 518 |
+
"step": 37500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.85,
|
| 522 |
+
"learning_rate": 1.2196724677858208e-05,
|
| 523 |
+
"loss": 0.0047,
|
| 524 |
+
"step": 38000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 5.93,
|
| 528 |
+
"learning_rate": 1.2094050002566869e-05,
|
| 529 |
+
"loss": 0.0046,
|
| 530 |
+
"step": 38500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.0,
|
| 534 |
+
"eval_accuracy": 0.9961636958386126,
|
| 535 |
+
"eval_f1": 0.9456837265483451,
|
| 536 |
+
"eval_loss": 0.01973150111734867,
|
| 537 |
+
"eval_precision": 0.9364702704788362,
|
| 538 |
+
"eval_recall": 0.955080277034472,
|
| 539 |
+
"eval_runtime": 49.6182,
|
| 540 |
+
"eval_samples_per_second": 448.021,
|
| 541 |
+
"eval_steps_per_second": 28.014,
|
| 542 |
+
"step": 38958
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 6.01,
|
| 546 |
+
"learning_rate": 1.199137532727553e-05,
|
| 547 |
+
"loss": 0.0043,
|
| 548 |
+
"step": 39000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.08,
|
| 552 |
+
"learning_rate": 1.1888700651984189e-05,
|
| 553 |
+
"loss": 0.003,
|
| 554 |
+
"step": 39500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.16,
|
| 558 |
+
"learning_rate": 1.178602597669285e-05,
|
| 559 |
+
"loss": 0.003,
|
| 560 |
+
"step": 40000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.24,
|
| 564 |
+
"learning_rate": 1.168335130140151e-05,
|
| 565 |
+
"loss": 0.0034,
|
| 566 |
+
"step": 40500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 6.31,
|
| 570 |
+
"learning_rate": 1.158067662611017e-05,
|
| 571 |
+
"loss": 0.0032,
|
| 572 |
+
"step": 41000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 6.39,
|
| 576 |
+
"learning_rate": 1.147800195081883e-05,
|
| 577 |
+
"loss": 0.0033,
|
| 578 |
+
"step": 41500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.47,
|
| 582 |
+
"learning_rate": 1.1375327275527492e-05,
|
| 583 |
+
"loss": 0.0033,
|
| 584 |
+
"step": 42000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.55,
|
| 588 |
+
"learning_rate": 1.1272652600236154e-05,
|
| 589 |
+
"loss": 0.0039,
|
| 590 |
+
"step": 42500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.62,
|
| 594 |
+
"learning_rate": 1.1169977924944813e-05,
|
| 595 |
+
"loss": 0.0035,
|
| 596 |
+
"step": 43000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.7,
|
| 600 |
+
"learning_rate": 1.1067303249653474e-05,
|
| 601 |
+
"loss": 0.0033,
|
| 602 |
+
"step": 43500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.78,
|
| 606 |
+
"learning_rate": 1.0964628574362135e-05,
|
| 607 |
+
"loss": 0.0042,
|
| 608 |
+
"step": 44000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 6.85,
|
| 612 |
+
"learning_rate": 1.0861953899070794e-05,
|
| 613 |
+
"loss": 0.0031,
|
| 614 |
+
"step": 44500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 6.93,
|
| 618 |
+
"learning_rate": 1.0759279223779455e-05,
|
| 619 |
+
"loss": 0.0036,
|
| 620 |
+
"step": 45000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7.0,
|
| 624 |
+
"eval_accuracy": 0.9965002975105203,
|
| 625 |
+
"eval_f1": 0.9516786640916097,
|
| 626 |
+
"eval_loss": 0.01960182562470436,
|
| 627 |
+
"eval_precision": 0.943634183140547,
|
| 628 |
+
"eval_recall": 0.9598614827640485,
|
| 629 |
+
"eval_runtime": 49.9435,
|
| 630 |
+
"eval_samples_per_second": 445.103,
|
| 631 |
+
"eval_steps_per_second": 27.831,
|
| 632 |
+
"step": 45451
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.01,
|
| 636 |
+
"learning_rate": 1.0656604548488116e-05,
|
| 637 |
+
"loss": 0.0032,
|
| 638 |
+
"step": 45500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.08,
|
| 642 |
+
"learning_rate": 1.0553929873196777e-05,
|
| 643 |
+
"loss": 0.002,
|
| 644 |
+
"step": 46000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.16,
|
| 648 |
+
"learning_rate": 1.0451255197905436e-05,
|
| 649 |
+
"loss": 0.0027,
|
| 650 |
+
"step": 46500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 7.24,
|
| 654 |
+
"learning_rate": 1.0348580522614099e-05,
|
| 655 |
+
"loss": 0.0023,
|
| 656 |
+
"step": 47000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 7.32,
|
| 660 |
+
"learning_rate": 1.024590584732276e-05,
|
| 661 |
+
"loss": 0.0026,
|
| 662 |
+
"step": 47500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 7.39,
|
| 666 |
+
"learning_rate": 1.014323117203142e-05,
|
| 667 |
+
"loss": 0.0027,
|
| 668 |
+
"step": 48000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.47,
|
| 672 |
+
"learning_rate": 1.004055649674008e-05,
|
| 673 |
+
"loss": 0.0024,
|
| 674 |
+
"step": 48500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.55,
|
| 678 |
+
"learning_rate": 9.93788182144874e-06,
|
| 679 |
+
"loss": 0.0034,
|
| 680 |
+
"step": 49000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 7.62,
|
| 684 |
+
"learning_rate": 9.835207146157401e-06,
|
| 685 |
+
"loss": 0.0029,
|
| 686 |
+
"step": 49500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 7.7,
|
| 690 |
+
"learning_rate": 9.732532470866062e-06,
|
| 691 |
+
"loss": 0.0029,
|
| 692 |
+
"step": 50000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 7.78,
|
| 696 |
+
"learning_rate": 9.629857795574721e-06,
|
| 697 |
+
"loss": 0.0026,
|
| 698 |
+
"step": 50500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 7.85,
|
| 702 |
+
"learning_rate": 9.527183120283382e-06,
|
| 703 |
+
"loss": 0.0029,
|
| 704 |
+
"step": 51000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 7.93,
|
| 708 |
+
"learning_rate": 9.424508444992043e-06,
|
| 709 |
+
"loss": 0.0032,
|
| 710 |
+
"step": 51500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 8.0,
|
| 714 |
+
"eval_accuracy": 0.9965701244530969,
|
| 715 |
+
"eval_f1": 0.951712302051642,
|
| 716 |
+
"eval_loss": 0.020936153829097748,
|
| 717 |
+
"eval_precision": 0.9433962264150944,
|
| 718 |
+
"eval_recall": 0.9601762946639383,
|
| 719 |
+
"eval_runtime": 49.9608,
|
| 720 |
+
"eval_samples_per_second": 444.949,
|
| 721 |
+
"eval_steps_per_second": 27.822,
|
| 722 |
+
"step": 51944
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 8.01,
|
| 726 |
+
"learning_rate": 9.321833769700704e-06,
|
| 727 |
+
"loss": 0.002,
|
| 728 |
+
"step": 52000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.09,
|
| 732 |
+
"learning_rate": 9.219159094409365e-06,
|
| 733 |
+
"loss": 0.0016,
|
| 734 |
+
"step": 52500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 8.16,
|
| 738 |
+
"learning_rate": 9.116484419118026e-06,
|
| 739 |
+
"loss": 0.0021,
|
| 740 |
+
"step": 53000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 8.24,
|
| 744 |
+
"learning_rate": 9.013809743826687e-06,
|
| 745 |
+
"loss": 0.002,
|
| 746 |
+
"step": 53500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.32,
|
| 750 |
+
"learning_rate": 8.911135068535346e-06,
|
| 751 |
+
"loss": 0.0021,
|
| 752 |
+
"step": 54000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 8.39,
|
| 756 |
+
"learning_rate": 8.808460393244007e-06,
|
| 757 |
+
"loss": 0.0024,
|
| 758 |
+
"step": 54500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 8.47,
|
| 762 |
+
"learning_rate": 8.705785717952668e-06,
|
| 763 |
+
"loss": 0.0021,
|
| 764 |
+
"step": 55000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 8.55,
|
| 768 |
+
"learning_rate": 8.603111042661328e-06,
|
| 769 |
+
"loss": 0.0019,
|
| 770 |
+
"step": 55500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.62,
|
| 774 |
+
"learning_rate": 8.50043636736999e-06,
|
| 775 |
+
"loss": 0.0021,
|
| 776 |
+
"step": 56000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 8.7,
|
| 780 |
+
"learning_rate": 8.39776169207865e-06,
|
| 781 |
+
"loss": 0.0021,
|
| 782 |
+
"step": 56500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 8.78,
|
| 786 |
+
"learning_rate": 8.29508701678731e-06,
|
| 787 |
+
"loss": 0.0024,
|
| 788 |
+
"step": 57000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 8.86,
|
| 792 |
+
"learning_rate": 8.19241234149597e-06,
|
| 793 |
+
"loss": 0.0022,
|
| 794 |
+
"step": 57500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 8.93,
|
| 798 |
+
"learning_rate": 8.089737666204631e-06,
|
| 799 |
+
"loss": 0.0025,
|
| 800 |
+
"step": 58000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 9.0,
|
| 804 |
+
"eval_accuracy": 0.9967020197890749,
|
| 805 |
+
"eval_f1": 0.9540931793351022,
|
| 806 |
+
"eval_loss": 0.02170099876821041,
|
| 807 |
+
"eval_precision": 0.9461190218232471,
|
| 808 |
+
"eval_recall": 0.962202896269479,
|
| 809 |
+
"eval_runtime": 57.3501,
|
| 810 |
+
"eval_samples_per_second": 387.619,
|
| 811 |
+
"eval_steps_per_second": 24.237,
|
| 812 |
+
"step": 58437
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 9.01,
|
| 816 |
+
"learning_rate": 7.987062990913292e-06,
|
| 817 |
+
"loss": 0.0023,
|
| 818 |
+
"step": 58500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.09,
|
| 822 |
+
"learning_rate": 7.884388315621953e-06,
|
| 823 |
+
"loss": 0.0018,
|
| 824 |
+
"step": 59000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.16,
|
| 828 |
+
"learning_rate": 7.781713640330612e-06,
|
| 829 |
+
"loss": 0.0013,
|
| 830 |
+
"step": 59500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 9.24,
|
| 834 |
+
"learning_rate": 7.679038965039273e-06,
|
| 835 |
+
"loss": 0.0018,
|
| 836 |
+
"step": 60000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 9.32,
|
| 840 |
+
"learning_rate": 7.576364289747934e-06,
|
| 841 |
+
"loss": 0.0016,
|
| 842 |
+
"step": 60500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 9.39,
|
| 846 |
+
"learning_rate": 7.473689614456595e-06,
|
| 847 |
+
"loss": 0.0012,
|
| 848 |
+
"step": 61000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 9.47,
|
| 852 |
+
"learning_rate": 7.371014939165256e-06,
|
| 853 |
+
"loss": 0.0014,
|
| 854 |
+
"step": 61500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 9.55,
|
| 858 |
+
"learning_rate": 7.2683402638739165e-06,
|
| 859 |
+
"loss": 0.0016,
|
| 860 |
+
"step": 62000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 9.63,
|
| 864 |
+
"learning_rate": 7.1656655885825765e-06,
|
| 865 |
+
"loss": 0.0015,
|
| 866 |
+
"step": 62500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 9.7,
|
| 870 |
+
"learning_rate": 7.062990913291237e-06,
|
| 871 |
+
"loss": 0.0015,
|
| 872 |
+
"step": 63000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 9.78,
|
| 876 |
+
"learning_rate": 6.960316237999898e-06,
|
| 877 |
+
"loss": 0.0015,
|
| 878 |
+
"step": 63500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 9.86,
|
| 882 |
+
"learning_rate": 6.857641562708558e-06,
|
| 883 |
+
"loss": 0.0017,
|
| 884 |
+
"step": 64000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 9.93,
|
| 888 |
+
"learning_rate": 6.754966887417219e-06,
|
| 889 |
+
"loss": 0.0015,
|
| 890 |
+
"step": 64500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 10.0,
|
| 894 |
+
"eval_accuracy": 0.9968685301906037,
|
| 895 |
+
"eval_f1": 0.9565455149112359,
|
| 896 |
+
"eval_loss": 0.02480412647128105,
|
| 897 |
+
"eval_precision": 0.9495172734674887,
|
| 898 |
+
"eval_recall": 0.9636785770502125,
|
| 899 |
+
"eval_runtime": 49.7243,
|
| 900 |
+
"eval_samples_per_second": 447.065,
|
| 901 |
+
"eval_steps_per_second": 27.954,
|
| 902 |
+
"step": 64930
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 10.01,
|
| 906 |
+
"learning_rate": 6.652292212125879e-06,
|
| 907 |
+
"loss": 0.0014,
|
| 908 |
+
"step": 65000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 10.09,
|
| 912 |
+
"learning_rate": 6.54961753683454e-06,
|
| 913 |
+
"loss": 0.0014,
|
| 914 |
+
"step": 65500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 10.16,
|
| 918 |
+
"learning_rate": 6.446942861543201e-06,
|
| 919 |
+
"loss": 0.0011,
|
| 920 |
+
"step": 66000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 10.24,
|
| 924 |
+
"learning_rate": 6.344268186251862e-06,
|
| 925 |
+
"loss": 0.001,
|
| 926 |
+
"step": 66500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 10.32,
|
| 930 |
+
"learning_rate": 6.241593510960522e-06,
|
| 931 |
+
"loss": 0.0011,
|
| 932 |
+
"step": 67000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 10.4,
|
| 936 |
+
"learning_rate": 6.138918835669183e-06,
|
| 937 |
+
"loss": 0.0011,
|
| 938 |
+
"step": 67500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 10.47,
|
| 942 |
+
"learning_rate": 6.036244160377844e-06,
|
| 943 |
+
"loss": 0.0012,
|
| 944 |
+
"step": 68000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 10.55,
|
| 948 |
+
"learning_rate": 5.9335694850865045e-06,
|
| 949 |
+
"loss": 0.0014,
|
| 950 |
+
"step": 68500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 10.63,
|
| 954 |
+
"learning_rate": 5.8308948097951645e-06,
|
| 955 |
+
"loss": 0.0011,
|
| 956 |
+
"step": 69000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 10.7,
|
| 960 |
+
"learning_rate": 5.7282201345038246e-06,
|
| 961 |
+
"loss": 0.0014,
|
| 962 |
+
"step": 69500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 10.78,
|
| 966 |
+
"learning_rate": 5.6255454592124854e-06,
|
| 967 |
+
"loss": 0.0011,
|
| 968 |
+
"step": 70000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 10.86,
|
| 972 |
+
"learning_rate": 5.522870783921146e-06,
|
| 973 |
+
"loss": 0.0011,
|
| 974 |
+
"step": 70500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 10.93,
|
| 978 |
+
"learning_rate": 5.420196108629807e-06,
|
| 979 |
+
"loss": 0.0013,
|
| 980 |
+
"step": 71000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 11.0,
|
| 984 |
+
"eval_accuracy": 0.9969544710430056,
|
| 985 |
+
"eval_f1": 0.9577580314422419,
|
| 986 |
+
"eval_loss": 0.026760583743453026,
|
| 987 |
+
"eval_precision": 0.9506842941883457,
|
| 988 |
+
"eval_recall": 0.9649378246497717,
|
| 989 |
+
"eval_runtime": 50.1368,
|
| 990 |
+
"eval_samples_per_second": 443.387,
|
| 991 |
+
"eval_steps_per_second": 27.724,
|
| 992 |
+
"step": 71423
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 11.01,
|
| 996 |
+
"learning_rate": 5.317521433338467e-06,
|
| 997 |
+
"loss": 0.0012,
|
| 998 |
+
"step": 71500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 11.09,
|
| 1002 |
+
"learning_rate": 5.214846758047128e-06,
|
| 1003 |
+
"loss": 0.001,
|
| 1004 |
+
"step": 72000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 11.17,
|
| 1008 |
+
"learning_rate": 5.112172082755789e-06,
|
| 1009 |
+
"loss": 0.001,
|
| 1010 |
+
"step": 72500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 11.24,
|
| 1014 |
+
"learning_rate": 5.00949740746445e-06,
|
| 1015 |
+
"loss": 0.001,
|
| 1016 |
+
"step": 73000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 11.32,
|
| 1020 |
+
"learning_rate": 4.90682273217311e-06,
|
| 1021 |
+
"loss": 0.0013,
|
| 1022 |
+
"step": 73500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 11.4,
|
| 1026 |
+
"learning_rate": 4.804148056881771e-06,
|
| 1027 |
+
"loss": 0.0009,
|
| 1028 |
+
"step": 74000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 11.47,
|
| 1032 |
+
"learning_rate": 4.701473381590432e-06,
|
| 1033 |
+
"loss": 0.001,
|
| 1034 |
+
"step": 74500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 11.55,
|
| 1038 |
+
"learning_rate": 4.598798706299092e-06,
|
| 1039 |
+
"loss": 0.0009,
|
| 1040 |
+
"step": 75000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 11.63,
|
| 1044 |
+
"learning_rate": 4.4961240310077525e-06,
|
| 1045 |
+
"loss": 0.001,
|
| 1046 |
+
"step": 75500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 11.7,
|
| 1050 |
+
"learning_rate": 4.393449355716413e-06,
|
| 1051 |
+
"loss": 0.0008,
|
| 1052 |
+
"step": 76000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 11.78,
|
| 1056 |
+
"learning_rate": 4.2907746804250734e-06,
|
| 1057 |
+
"loss": 0.0011,
|
| 1058 |
+
"step": 76500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 11.86,
|
| 1062 |
+
"learning_rate": 4.188100005133734e-06,
|
| 1063 |
+
"loss": 0.0008,
|
| 1064 |
+
"step": 77000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 11.94,
|
| 1068 |
+
"learning_rate": 4.085425329842394e-06,
|
| 1069 |
+
"loss": 0.001,
|
| 1070 |
+
"step": 77500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 12.0,
|
| 1074 |
+
"eval_accuracy": 0.9969103069938546,
|
| 1075 |
+
"eval_f1": 0.957125828073398,
|
| 1076 |
+
"eval_loss": 0.027535809203982353,
|
| 1077 |
+
"eval_precision": 0.9506424440045029,
|
| 1078 |
+
"eval_recall": 0.9636982527939556,
|
| 1079 |
+
"eval_runtime": 49.2131,
|
| 1080 |
+
"eval_samples_per_second": 451.709,
|
| 1081 |
+
"eval_steps_per_second": 28.245,
|
| 1082 |
+
"step": 77916
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 12.01,
|
| 1086 |
+
"learning_rate": 3.982750654551055e-06,
|
| 1087 |
+
"loss": 0.0009,
|
| 1088 |
+
"step": 78000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 12.09,
|
| 1092 |
+
"learning_rate": 3.880075979259716e-06,
|
| 1093 |
+
"loss": 0.0009,
|
| 1094 |
+
"step": 78500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 12.17,
|
| 1098 |
+
"learning_rate": 3.7774013039683766e-06,
|
| 1099 |
+
"loss": 0.0008,
|
| 1100 |
+
"step": 79000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 12.24,
|
| 1104 |
+
"learning_rate": 3.6747266286770374e-06,
|
| 1105 |
+
"loss": 0.0009,
|
| 1106 |
+
"step": 79500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 12.32,
|
| 1110 |
+
"learning_rate": 3.572051953385698e-06,
|
| 1111 |
+
"loss": 0.0007,
|
| 1112 |
+
"step": 80000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 12.4,
|
| 1116 |
+
"learning_rate": 3.4693772780943583e-06,
|
| 1117 |
+
"loss": 0.0009,
|
| 1118 |
+
"step": 80500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 12.47,
|
| 1122 |
+
"learning_rate": 3.366702602803019e-06,
|
| 1123 |
+
"loss": 0.0008,
|
| 1124 |
+
"step": 81000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 12.55,
|
| 1128 |
+
"learning_rate": 3.2640279275116792e-06,
|
| 1129 |
+
"loss": 0.0008,
|
| 1130 |
+
"step": 81500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 12.63,
|
| 1134 |
+
"learning_rate": 3.16135325222034e-06,
|
| 1135 |
+
"loss": 0.0007,
|
| 1136 |
+
"step": 82000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 12.71,
|
| 1140 |
+
"learning_rate": 3.0586785769290006e-06,
|
| 1141 |
+
"loss": 0.001,
|
| 1142 |
+
"step": 82500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 12.78,
|
| 1146 |
+
"learning_rate": 2.9560039016376615e-06,
|
| 1147 |
+
"loss": 0.0008,
|
| 1148 |
+
"step": 83000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 12.86,
|
| 1152 |
+
"learning_rate": 2.853329226346322e-06,
|
| 1153 |
+
"loss": 0.0009,
|
| 1154 |
+
"step": 83500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 12.94,
|
| 1158 |
+
"learning_rate": 2.7506545510549828e-06,
|
| 1159 |
+
"loss": 0.0008,
|
| 1160 |
+
"step": 84000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 13.0,
|
| 1164 |
+
"eval_accuracy": 0.9971054643461841,
|
| 1165 |
+
"eval_f1": 0.9594136437572266,
|
| 1166 |
+
"eval_loss": 0.026200518012046814,
|
| 1167 |
+
"eval_precision": 0.9556119461253172,
|
| 1168 |
+
"eval_recall": 0.963245710687864,
|
| 1169 |
+
"eval_runtime": 48.4168,
|
| 1170 |
+
"eval_samples_per_second": 459.138,
|
| 1171 |
+
"eval_steps_per_second": 28.709,
|
| 1172 |
+
"step": 84409
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 13.01,
|
| 1176 |
+
"learning_rate": 2.6479798757636432e-06,
|
| 1177 |
+
"loss": 0.0007,
|
| 1178 |
+
"step": 84500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 13.09,
|
| 1182 |
+
"learning_rate": 2.5453052004723037e-06,
|
| 1183 |
+
"loss": 0.0006,
|
| 1184 |
+
"step": 85000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 13.17,
|
| 1188 |
+
"learning_rate": 2.442630525180964e-06,
|
| 1189 |
+
"loss": 0.0007,
|
| 1190 |
+
"step": 85500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 13.25,
|
| 1194 |
+
"learning_rate": 2.339955849889625e-06,
|
| 1195 |
+
"loss": 0.0006,
|
| 1196 |
+
"step": 86000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 13.32,
|
| 1200 |
+
"learning_rate": 2.2372811745982855e-06,
|
| 1201 |
+
"loss": 0.0006,
|
| 1202 |
+
"step": 86500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 13.4,
|
| 1206 |
+
"learning_rate": 2.1346064993069464e-06,
|
| 1207 |
+
"loss": 0.0008,
|
| 1208 |
+
"step": 87000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 13.48,
|
| 1212 |
+
"learning_rate": 2.031931824015607e-06,
|
| 1213 |
+
"loss": 0.0006,
|
| 1214 |
+
"step": 87500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 13.55,
|
| 1218 |
+
"learning_rate": 1.9292571487242673e-06,
|
| 1219 |
+
"loss": 0.0007,
|
| 1220 |
+
"step": 88000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 13.63,
|
| 1224 |
+
"learning_rate": 1.826582473432928e-06,
|
| 1225 |
+
"loss": 0.0005,
|
| 1226 |
+
"step": 88500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 13.71,
|
| 1230 |
+
"learning_rate": 1.7239077981415886e-06,
|
| 1231 |
+
"loss": 0.0006,
|
| 1232 |
+
"step": 89000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 13.78,
|
| 1236 |
+
"learning_rate": 1.6212331228502493e-06,
|
| 1237 |
+
"loss": 0.0007,
|
| 1238 |
+
"step": 89500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 13.86,
|
| 1242 |
+
"learning_rate": 1.5185584475589097e-06,
|
| 1243 |
+
"loss": 0.0008,
|
| 1244 |
+
"step": 90000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 13.94,
|
| 1248 |
+
"learning_rate": 1.4158837722675704e-06,
|
| 1249 |
+
"loss": 0.0006,
|
| 1250 |
+
"step": 90500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 14.0,
|
| 1254 |
+
"eval_accuracy": 0.9970839791330836,
|
| 1255 |
+
"eval_f1": 0.9592343002246313,
|
| 1256 |
+
"eval_loss": 0.028846312314271927,
|
| 1257 |
+
"eval_precision": 0.952332932552457,
|
| 1258 |
+
"eval_recall": 0.9662364237368173,
|
| 1259 |
+
"eval_runtime": 49.5216,
|
| 1260 |
+
"eval_samples_per_second": 448.895,
|
| 1261 |
+
"eval_steps_per_second": 28.069,
|
| 1262 |
+
"step": 90902
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 14.02,
|
| 1266 |
+
"learning_rate": 1.313209096976231e-06,
|
| 1267 |
+
"loss": 0.0007,
|
| 1268 |
+
"step": 91000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 14.09,
|
| 1272 |
+
"learning_rate": 1.2105344216848915e-06,
|
| 1273 |
+
"loss": 0.0006,
|
| 1274 |
+
"step": 91500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 14.17,
|
| 1278 |
+
"learning_rate": 1.1078597463935522e-06,
|
| 1279 |
+
"loss": 0.0004,
|
| 1280 |
+
"step": 92000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 14.25,
|
| 1284 |
+
"learning_rate": 1.0051850711022128e-06,
|
| 1285 |
+
"loss": 0.0004,
|
| 1286 |
+
"step": 92500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 14.32,
|
| 1290 |
+
"learning_rate": 9.025103958108733e-07,
|
| 1291 |
+
"loss": 0.0006,
|
| 1292 |
+
"step": 93000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 14.4,
|
| 1296 |
+
"learning_rate": 7.998357205195339e-07,
|
| 1297 |
+
"loss": 0.0005,
|
| 1298 |
+
"step": 93500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 14.48,
|
| 1302 |
+
"learning_rate": 6.971610452281945e-07,
|
| 1303 |
+
"loss": 0.0004,
|
| 1304 |
+
"step": 94000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 14.55,
|
| 1308 |
+
"learning_rate": 5.944863699368552e-07,
|
| 1309 |
+
"loss": 0.0005,
|
| 1310 |
+
"step": 94500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 14.63,
|
| 1314 |
+
"learning_rate": 4.918116946455157e-07,
|
| 1315 |
+
"loss": 0.0005,
|
| 1316 |
+
"step": 95000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 14.71,
|
| 1320 |
+
"learning_rate": 3.891370193541763e-07,
|
| 1321 |
+
"loss": 0.0005,
|
| 1322 |
+
"step": 95500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 14.79,
|
| 1326 |
+
"learning_rate": 2.8646234406283695e-07,
|
| 1327 |
+
"loss": 0.0006,
|
| 1328 |
+
"step": 96000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 14.86,
|
| 1332 |
+
"learning_rate": 1.837876687714975e-07,
|
| 1333 |
+
"loss": 0.0005,
|
| 1334 |
+
"step": 96500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 14.94,
|
| 1338 |
+
"learning_rate": 8.111299348015812e-08,
|
| 1339 |
+
"loss": 0.0005,
|
| 1340 |
+
"step": 97000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 15.0,
|
| 1344 |
+
"eval_accuracy": 0.9971162069527343,
|
| 1345 |
+
"eval_f1": 0.960166445260608,
|
| 1346 |
+
"eval_loss": 0.03031528927385807,
|
| 1347 |
+
"eval_precision": 0.9533868715083799,
|
| 1348 |
+
"eval_recall": 0.9670431292302849,
|
| 1349 |
+
"eval_runtime": 56.2527,
|
| 1350 |
+
"eval_samples_per_second": 395.181,
|
| 1351 |
+
"eval_steps_per_second": 24.71,
|
| 1352 |
+
"step": 97395
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 15.0,
|
| 1356 |
+
"step": 97395,
|
| 1357 |
+
"total_flos": 4.071562837460255e+17,
|
| 1358 |
+
"train_loss": 0.0005194992909466218,
|
| 1359 |
+
"train_runtime": 2998.8244,
|
| 1360 |
+
"train_samples_per_second": 519.599,
|
| 1361 |
+
"train_steps_per_second": 32.478
|
| 1362 |
+
}
|
| 1363 |
+
],
|
| 1364 |
+
"max_steps": 97395,
|
| 1365 |
+
"num_train_epochs": 15,
|
| 1366 |
+
"total_flos": 4.071562837460255e+17,
|
| 1367 |
+
"trial_name": null,
|
| 1368 |
+
"trial_params": null
|
| 1369 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f392fbc2c8c80ebe7c313be7c45f2d118aaa6732d304983fe173acec45b12b5d
|
| 3 |
+
size 3119
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|