LL
commited on
Commit
•
b70a5c4
1
Parent(s):
1580272
update files
Browse files- all_results.json +14 -0
- config.json +27 -0
- eval_results.json +11 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- test_results.json +11 -0
- tokenizer_config.json +1 -0
- train_results.json +6 -0
- trainer_state.json +1247 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8719441210710128,
|
| 4 |
+
"eval_f1": 0.802158273381295,
|
| 5 |
+
"eval_loss": 0.34718233346939087,
|
| 6 |
+
"eval_precision": 0.8050541516245487,
|
| 7 |
+
"eval_recall": 0.7992831541218638,
|
| 8 |
+
"eval_runtime": 5.0547,
|
| 9 |
+
"eval_samples": 859,
|
| 10 |
+
"eval_samples_per_second": 169.94,
|
| 11 |
+
"train_runtime": 1963.3463,
|
| 12 |
+
"train_samples": 15385,
|
| 13 |
+
"train_samples_per_second": 0.185
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "results/qa-suffix-roberta-large-2e-5-32/checkpoint-330",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"finetuning_task": "deft_task1",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 16,
|
| 20 |
+
"num_hidden_layers": 24,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"transformers_version": "4.5.0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8956422018348624,
|
| 4 |
+
"eval_f1": 0.8400702987697716,
|
| 5 |
+
"eval_loss": 0.2676824629306793,
|
| 6 |
+
"eval_precision": 0.8385964912280702,
|
| 7 |
+
"eval_recall": 0.8415492957746479,
|
| 8 |
+
"eval_runtime": 4.9752,
|
| 9 |
+
"eval_samples": 872,
|
| 10 |
+
"eval_samples_per_second": 175.271
|
| 11 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bffabb324e8b3d091443797487d417115fa7a93cdf19acb00aa0dc72d1b84079
|
| 3 |
+
size 1421620681
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
test_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8719441210710128,
|
| 4 |
+
"eval_f1": 0.802158273381295,
|
| 5 |
+
"eval_loss": 0.34718233346939087,
|
| 6 |
+
"eval_precision": 0.8050541516245487,
|
| 7 |
+
"eval_recall": 0.7992831541218638,
|
| 8 |
+
"eval_runtime": 5.0547,
|
| 9 |
+
"eval_samples": 859,
|
| 10 |
+
"eval_samples_per_second": 169.94
|
| 11 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large"}
|
train_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_runtime": 1963.3463,
|
| 4 |
+
"train_samples": 15385,
|
| 5 |
+
"train_samples_per_second": 0.185
|
| 6 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1247 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8400702987697716,
|
| 3 |
+
"best_model_checkpoint": "results/qa-suffix-roberta-large-2e-5-32/checkpoint-330",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 363,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 2.702702702702703e-06,
|
| 13 |
+
"loss": 0.656,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"eval_accuracy": 0.6743119266055045,
|
| 19 |
+
"eval_f1": 0.0,
|
| 20 |
+
"eval_loss": 0.638568639755249,
|
| 21 |
+
"eval_precision": 0.0,
|
| 22 |
+
"eval_recall": 0.0,
|
| 23 |
+
"eval_runtime": 7.0752,
|
| 24 |
+
"eval_samples_per_second": 123.248,
|
| 25 |
+
"step": 5
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.08,
|
| 29 |
+
"learning_rate": 5.405405405405406e-06,
|
| 30 |
+
"loss": 0.6251,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"eval_accuracy": 0.6743119266055045,
|
| 36 |
+
"eval_f1": 0.0,
|
| 37 |
+
"eval_loss": 0.6357823610305786,
|
| 38 |
+
"eval_precision": 0.0,
|
| 39 |
+
"eval_recall": 0.0,
|
| 40 |
+
"eval_runtime": 6.4162,
|
| 41 |
+
"eval_samples_per_second": 135.907,
|
| 42 |
+
"step": 10
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.12,
|
| 46 |
+
"learning_rate": 8.108108108108109e-06,
|
| 47 |
+
"loss": 0.6534,
|
| 48 |
+
"step": 15
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.12,
|
| 52 |
+
"eval_accuracy": 0.6743119266055045,
|
| 53 |
+
"eval_f1": 0.0,
|
| 54 |
+
"eval_loss": 0.6329530477523804,
|
| 55 |
+
"eval_precision": 0.0,
|
| 56 |
+
"eval_recall": 0.0,
|
| 57 |
+
"eval_runtime": 5.2772,
|
| 58 |
+
"eval_samples_per_second": 165.241,
|
| 59 |
+
"step": 15
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17,
|
| 63 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 64 |
+
"loss": 0.6362,
|
| 65 |
+
"step": 20
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17,
|
| 69 |
+
"eval_accuracy": 0.6743119266055045,
|
| 70 |
+
"eval_f1": 0.0,
|
| 71 |
+
"eval_loss": 0.62663733959198,
|
| 72 |
+
"eval_precision": 0.0,
|
| 73 |
+
"eval_recall": 0.0,
|
| 74 |
+
"eval_runtime": 7.1397,
|
| 75 |
+
"eval_samples_per_second": 122.133,
|
| 76 |
+
"step": 20
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.21,
|
| 80 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 81 |
+
"loss": 0.6653,
|
| 82 |
+
"step": 25
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.21,
|
| 86 |
+
"eval_accuracy": 0.6743119266055045,
|
| 87 |
+
"eval_f1": 0.0,
|
| 88 |
+
"eval_loss": 0.614637017250061,
|
| 89 |
+
"eval_precision": 0.0,
|
| 90 |
+
"eval_recall": 0.0,
|
| 91 |
+
"eval_runtime": 5.5244,
|
| 92 |
+
"eval_samples_per_second": 157.845,
|
| 93 |
+
"step": 25
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25,
|
| 97 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 98 |
+
"loss": 0.5946,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.25,
|
| 103 |
+
"eval_accuracy": 0.6926605504587156,
|
| 104 |
+
"eval_f1": 0.1518987341772152,
|
| 105 |
+
"eval_loss": 0.5719833374023438,
|
| 106 |
+
"eval_precision": 0.75,
|
| 107 |
+
"eval_recall": 0.08450704225352113,
|
| 108 |
+
"eval_runtime": 6.0074,
|
| 109 |
+
"eval_samples_per_second": 145.154,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.29,
|
| 114 |
+
"learning_rate": 1.891891891891892e-05,
|
| 115 |
+
"loss": 0.5597,
|
| 116 |
+
"step": 35
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.29,
|
| 120 |
+
"eval_accuracy": 0.783256880733945,
|
| 121 |
+
"eval_f1": 0.5900216919739696,
|
| 122 |
+
"eval_loss": 0.4864228665828705,
|
| 123 |
+
"eval_precision": 0.768361581920904,
|
| 124 |
+
"eval_recall": 0.4788732394366197,
|
| 125 |
+
"eval_runtime": 7.545,
|
| 126 |
+
"eval_samples_per_second": 115.574,
|
| 127 |
+
"step": 35
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.33,
|
| 131 |
+
"learning_rate": 1.98159509202454e-05,
|
| 132 |
+
"loss": 0.5029,
|
| 133 |
+
"step": 40
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.33,
|
| 137 |
+
"eval_accuracy": 0.7259174311926605,
|
| 138 |
+
"eval_f1": 0.31123919308357345,
|
| 139 |
+
"eval_loss": 0.5254184603691101,
|
| 140 |
+
"eval_precision": 0.8571428571428571,
|
| 141 |
+
"eval_recall": 0.19014084507042253,
|
| 142 |
+
"eval_runtime": 7.5551,
|
| 143 |
+
"eval_samples_per_second": 115.418,
|
| 144 |
+
"step": 40
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.37,
|
| 148 |
+
"learning_rate": 1.9509202453987733e-05,
|
| 149 |
+
"loss": 0.5271,
|
| 150 |
+
"step": 45
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.37,
|
| 154 |
+
"eval_accuracy": 0.8360091743119266,
|
| 155 |
+
"eval_f1": 0.7265774378585086,
|
| 156 |
+
"eval_loss": 0.41283223032951355,
|
| 157 |
+
"eval_precision": 0.7949790794979079,
|
| 158 |
+
"eval_recall": 0.6690140845070423,
|
| 159 |
+
"eval_runtime": 6.2573,
|
| 160 |
+
"eval_samples_per_second": 139.357,
|
| 161 |
+
"step": 45
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.41,
|
| 165 |
+
"learning_rate": 1.9202453987730062e-05,
|
| 166 |
+
"loss": 0.4492,
|
| 167 |
+
"step": 50
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.41,
|
| 171 |
+
"eval_accuracy": 0.8532110091743119,
|
| 172 |
+
"eval_f1": 0.7714285714285714,
|
| 173 |
+
"eval_loss": 0.3917687237262726,
|
| 174 |
+
"eval_precision": 0.782608695652174,
|
| 175 |
+
"eval_recall": 0.7605633802816901,
|
| 176 |
+
"eval_runtime": 5.3023,
|
| 177 |
+
"eval_samples_per_second": 164.456,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.45,
|
| 182 |
+
"learning_rate": 1.8895705521472395e-05,
|
| 183 |
+
"loss": 0.4193,
|
| 184 |
+
"step": 55
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.45,
|
| 188 |
+
"eval_accuracy": 0.8394495412844036,
|
| 189 |
+
"eval_f1": 0.7188755020080323,
|
| 190 |
+
"eval_loss": 0.35428276658058167,
|
| 191 |
+
"eval_precision": 0.8364485981308412,
|
| 192 |
+
"eval_recall": 0.6302816901408451,
|
| 193 |
+
"eval_runtime": 7.0485,
|
| 194 |
+
"eval_samples_per_second": 123.714,
|
| 195 |
+
"step": 55
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.5,
|
| 199 |
+
"learning_rate": 1.8588957055214724e-05,
|
| 200 |
+
"loss": 0.369,
|
| 201 |
+
"step": 60
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.5,
|
| 205 |
+
"eval_accuracy": 0.8428899082568807,
|
| 206 |
+
"eval_f1": 0.7674023769100169,
|
| 207 |
+
"eval_loss": 0.37413832545280457,
|
| 208 |
+
"eval_precision": 0.740983606557377,
|
| 209 |
+
"eval_recall": 0.795774647887324,
|
| 210 |
+
"eval_runtime": 7.2795,
|
| 211 |
+
"eval_samples_per_second": 119.788,
|
| 212 |
+
"step": 60
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.54,
|
| 216 |
+
"learning_rate": 1.828220858895706e-05,
|
| 217 |
+
"loss": 0.4063,
|
| 218 |
+
"step": 65
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.54,
|
| 222 |
+
"eval_accuracy": 0.8096330275229358,
|
| 223 |
+
"eval_f1": 0.7558823529411764,
|
| 224 |
+
"eval_loss": 0.4283739924430847,
|
| 225 |
+
"eval_precision": 0.648989898989899,
|
| 226 |
+
"eval_recall": 0.9049295774647887,
|
| 227 |
+
"eval_runtime": 6.9732,
|
| 228 |
+
"eval_samples_per_second": 125.05,
|
| 229 |
+
"step": 65
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.58,
|
| 233 |
+
"learning_rate": 1.797546012269939e-05,
|
| 234 |
+
"loss": 0.4608,
|
| 235 |
+
"step": 70
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.58,
|
| 239 |
+
"eval_accuracy": 0.8348623853211009,
|
| 240 |
+
"eval_f1": 0.6869565217391304,
|
| 241 |
+
"eval_loss": 0.37825068831443787,
|
| 242 |
+
"eval_precision": 0.8977272727272727,
|
| 243 |
+
"eval_recall": 0.5563380281690141,
|
| 244 |
+
"eval_runtime": 5.0,
|
| 245 |
+
"eval_samples_per_second": 174.401,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.62,
|
| 250 |
+
"learning_rate": 1.766871165644172e-05,
|
| 251 |
+
"loss": 0.4506,
|
| 252 |
+
"step": 75
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.62,
|
| 256 |
+
"eval_accuracy": 0.8681192660550459,
|
| 257 |
+
"eval_f1": 0.8067226890756302,
|
| 258 |
+
"eval_loss": 0.3225836753845215,
|
| 259 |
+
"eval_precision": 0.7717041800643086,
|
| 260 |
+
"eval_recall": 0.8450704225352113,
|
| 261 |
+
"eval_runtime": 6.6965,
|
| 262 |
+
"eval_samples_per_second": 130.217,
|
| 263 |
+
"step": 75
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.66,
|
| 267 |
+
"learning_rate": 1.736196319018405e-05,
|
| 268 |
+
"loss": 0.3557,
|
| 269 |
+
"step": 80
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.66,
|
| 273 |
+
"eval_accuracy": 0.8497706422018348,
|
| 274 |
+
"eval_f1": 0.7883683360258481,
|
| 275 |
+
"eval_loss": 0.34664297103881836,
|
| 276 |
+
"eval_precision": 0.7283582089552239,
|
| 277 |
+
"eval_recall": 0.8591549295774648,
|
| 278 |
+
"eval_runtime": 7.1969,
|
| 279 |
+
"eval_samples_per_second": 121.162,
|
| 280 |
+
"step": 80
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7,
|
| 284 |
+
"learning_rate": 1.7055214723926382e-05,
|
| 285 |
+
"loss": 0.4147,
|
| 286 |
+
"step": 85
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.7,
|
| 290 |
+
"eval_accuracy": 0.8600917431192661,
|
| 291 |
+
"eval_f1": 0.7680608365019012,
|
| 292 |
+
"eval_loss": 0.3466174304485321,
|
| 293 |
+
"eval_precision": 0.8347107438016529,
|
| 294 |
+
"eval_recall": 0.7112676056338029,
|
| 295 |
+
"eval_runtime": 7.3038,
|
| 296 |
+
"eval_samples_per_second": 119.39,
|
| 297 |
+
"step": 85
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.74,
|
| 301 |
+
"learning_rate": 1.6748466257668714e-05,
|
| 302 |
+
"loss": 0.4009,
|
| 303 |
+
"step": 90
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.74,
|
| 307 |
+
"eval_accuracy": 0.8394495412844036,
|
| 308 |
+
"eval_f1": 0.779874213836478,
|
| 309 |
+
"eval_loss": 0.35522547364234924,
|
| 310 |
+
"eval_precision": 0.7045454545454546,
|
| 311 |
+
"eval_recall": 0.8732394366197183,
|
| 312 |
+
"eval_runtime": 5.9612,
|
| 313 |
+
"eval_samples_per_second": 146.278,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.79,
|
| 318 |
+
"learning_rate": 1.6441717791411043e-05,
|
| 319 |
+
"loss": 0.355,
|
| 320 |
+
"step": 95
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.79,
|
| 324 |
+
"eval_accuracy": 0.856651376146789,
|
| 325 |
+
"eval_f1": 0.7731397459165154,
|
| 326 |
+
"eval_loss": 0.33357954025268555,
|
| 327 |
+
"eval_precision": 0.797752808988764,
|
| 328 |
+
"eval_recall": 0.75,
|
| 329 |
+
"eval_runtime": 5.1139,
|
| 330 |
+
"eval_samples_per_second": 170.515,
|
| 331 |
+
"step": 95
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.83,
|
| 335 |
+
"learning_rate": 1.6134969325153376e-05,
|
| 336 |
+
"loss": 0.3783,
|
| 337 |
+
"step": 100
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.83,
|
| 341 |
+
"eval_accuracy": 0.8543577981651376,
|
| 342 |
+
"eval_f1": 0.7814113597246126,
|
| 343 |
+
"eval_loss": 0.3445069193840027,
|
| 344 |
+
"eval_precision": 0.7643097643097643,
|
| 345 |
+
"eval_recall": 0.7992957746478874,
|
| 346 |
+
"eval_runtime": 7.3177,
|
| 347 |
+
"eval_samples_per_second": 119.163,
|
| 348 |
+
"step": 100
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.87,
|
| 352 |
+
"learning_rate": 1.5828220858895708e-05,
|
| 353 |
+
"loss": 0.3407,
|
| 354 |
+
"step": 105
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.87,
|
| 358 |
+
"eval_accuracy": 0.8612385321100917,
|
| 359 |
+
"eval_f1": 0.7858407079646017,
|
| 360 |
+
"eval_loss": 0.3221452236175537,
|
| 361 |
+
"eval_precision": 0.7900355871886121,
|
| 362 |
+
"eval_recall": 0.7816901408450704,
|
| 363 |
+
"eval_runtime": 7.2195,
|
| 364 |
+
"eval_samples_per_second": 120.784,
|
| 365 |
+
"step": 105
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.91,
|
| 369 |
+
"learning_rate": 1.5521472392638037e-05,
|
| 370 |
+
"loss": 0.3886,
|
| 371 |
+
"step": 110
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.91,
|
| 375 |
+
"eval_accuracy": 0.8532110091743119,
|
| 376 |
+
"eval_f1": 0.7942122186495175,
|
| 377 |
+
"eval_loss": 0.3414439558982849,
|
| 378 |
+
"eval_precision": 0.7307692307692307,
|
| 379 |
+
"eval_recall": 0.8697183098591549,
|
| 380 |
+
"eval_runtime": 6.7246,
|
| 381 |
+
"eval_samples_per_second": 129.673,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.95,
|
| 386 |
+
"learning_rate": 1.5214723926380371e-05,
|
| 387 |
+
"loss": 0.3325,
|
| 388 |
+
"step": 115
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.95,
|
| 392 |
+
"eval_accuracy": 0.8646788990825688,
|
| 393 |
+
"eval_f1": 0.7999999999999999,
|
| 394 |
+
"eval_loss": 0.3119550347328186,
|
| 395 |
+
"eval_precision": 0.7712418300653595,
|
| 396 |
+
"eval_recall": 0.8309859154929577,
|
| 397 |
+
"eval_runtime": 5.1226,
|
| 398 |
+
"eval_samples_per_second": 170.227,
|
| 399 |
+
"step": 115
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.99,
|
| 403 |
+
"learning_rate": 1.4907975460122702e-05,
|
| 404 |
+
"loss": 0.3489,
|
| 405 |
+
"step": 120
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.99,
|
| 409 |
+
"eval_accuracy": 0.8669724770642202,
|
| 410 |
+
"eval_f1": 0.802721088435374,
|
| 411 |
+
"eval_loss": 0.3048677444458008,
|
| 412 |
+
"eval_precision": 0.7763157894736842,
|
| 413 |
+
"eval_recall": 0.8309859154929577,
|
| 414 |
+
"eval_runtime": 5.8542,
|
| 415 |
+
"eval_samples_per_second": 148.952,
|
| 416 |
+
"step": 120
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.03,
|
| 420 |
+
"learning_rate": 1.4601226993865032e-05,
|
| 421 |
+
"loss": 0.308,
|
| 422 |
+
"step": 125
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.03,
|
| 426 |
+
"eval_accuracy": 0.8772935779816514,
|
| 427 |
+
"eval_f1": 0.8112874779541447,
|
| 428 |
+
"eval_loss": 0.2938537299633026,
|
| 429 |
+
"eval_precision": 0.8127208480565371,
|
| 430 |
+
"eval_recall": 0.8098591549295775,
|
| 431 |
+
"eval_runtime": 7.2512,
|
| 432 |
+
"eval_samples_per_second": 120.256,
|
| 433 |
+
"step": 125
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.07,
|
| 437 |
+
"learning_rate": 1.4294478527607363e-05,
|
| 438 |
+
"loss": 0.3356,
|
| 439 |
+
"step": 130
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.07,
|
| 443 |
+
"eval_accuracy": 0.8704128440366973,
|
| 444 |
+
"eval_f1": 0.8027923211169284,
|
| 445 |
+
"eval_loss": 0.3023342192173004,
|
| 446 |
+
"eval_precision": 0.7958477508650519,
|
| 447 |
+
"eval_recall": 0.8098591549295775,
|
| 448 |
+
"eval_runtime": 7.3245,
|
| 449 |
+
"eval_samples_per_second": 119.053,
|
| 450 |
+
"step": 130
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.12,
|
| 454 |
+
"learning_rate": 1.3987730061349694e-05,
|
| 455 |
+
"loss": 0.3,
|
| 456 |
+
"step": 135
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.12,
|
| 460 |
+
"eval_accuracy": 0.8727064220183486,
|
| 461 |
+
"eval_f1": 0.8035398230088495,
|
| 462 |
+
"eval_loss": 0.3078989088535309,
|
| 463 |
+
"eval_precision": 0.8078291814946619,
|
| 464 |
+
"eval_recall": 0.7992957746478874,
|
| 465 |
+
"eval_runtime": 6.5413,
|
| 466 |
+
"eval_samples_per_second": 133.306,
|
| 467 |
+
"step": 135
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.16,
|
| 471 |
+
"learning_rate": 1.3680981595092026e-05,
|
| 472 |
+
"loss": 0.3106,
|
| 473 |
+
"step": 140
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.16,
|
| 477 |
+
"eval_accuracy": 0.8658256880733946,
|
| 478 |
+
"eval_f1": 0.8040201005025125,
|
| 479 |
+
"eval_loss": 0.3164271116256714,
|
| 480 |
+
"eval_precision": 0.7667731629392971,
|
| 481 |
+
"eval_recall": 0.8450704225352113,
|
| 482 |
+
"eval_runtime": 5.1365,
|
| 483 |
+
"eval_samples_per_second": 169.766,
|
| 484 |
+
"step": 140
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.2,
|
| 488 |
+
"learning_rate": 1.3374233128834357e-05,
|
| 489 |
+
"loss": 0.2401,
|
| 490 |
+
"step": 145
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.2,
|
| 494 |
+
"eval_accuracy": 0.8761467889908257,
|
| 495 |
+
"eval_f1": 0.8131487889273357,
|
| 496 |
+
"eval_loss": 0.3013850152492523,
|
| 497 |
+
"eval_precision": 0.7993197278911565,
|
| 498 |
+
"eval_recall": 0.8274647887323944,
|
| 499 |
+
"eval_runtime": 5.3284,
|
| 500 |
+
"eval_samples_per_second": 163.653,
|
| 501 |
+
"step": 145
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.24,
|
| 505 |
+
"learning_rate": 1.3067484662576687e-05,
|
| 506 |
+
"loss": 0.3167,
|
| 507 |
+
"step": 150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.24,
|
| 511 |
+
"eval_accuracy": 0.856651376146789,
|
| 512 |
+
"eval_f1": 0.7980613893376413,
|
| 513 |
+
"eval_loss": 0.32322707772254944,
|
| 514 |
+
"eval_precision": 0.7373134328358208,
|
| 515 |
+
"eval_recall": 0.8697183098591549,
|
| 516 |
+
"eval_runtime": 7.1641,
|
| 517 |
+
"eval_samples_per_second": 121.717,
|
| 518 |
+
"step": 150
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.28,
|
| 522 |
+
"learning_rate": 1.276073619631902e-05,
|
| 523 |
+
"loss": 0.3227,
|
| 524 |
+
"step": 155
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.28,
|
| 528 |
+
"eval_accuracy": 0.8761467889908257,
|
| 529 |
+
"eval_f1": 0.7954545454545454,
|
| 530 |
+
"eval_loss": 0.3056000769138336,
|
| 531 |
+
"eval_precision": 0.860655737704918,
|
| 532 |
+
"eval_recall": 0.7394366197183099,
|
| 533 |
+
"eval_runtime": 7.0886,
|
| 534 |
+
"eval_samples_per_second": 123.014,
|
| 535 |
+
"step": 155
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.32,
|
| 539 |
+
"learning_rate": 1.245398773006135e-05,
|
| 540 |
+
"loss": 0.3401,
|
| 541 |
+
"step": 160
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.32,
|
| 545 |
+
"eval_accuracy": 0.8646788990825688,
|
| 546 |
+
"eval_f1": 0.805921052631579,
|
| 547 |
+
"eval_loss": 0.30931735038757324,
|
| 548 |
+
"eval_precision": 0.7561728395061729,
|
| 549 |
+
"eval_recall": 0.8626760563380281,
|
| 550 |
+
"eval_runtime": 7.2974,
|
| 551 |
+
"eval_samples_per_second": 119.494,
|
| 552 |
+
"step": 160
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.36,
|
| 556 |
+
"learning_rate": 1.2147239263803683e-05,
|
| 557 |
+
"loss": 0.272,
|
| 558 |
+
"step": 165
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.36,
|
| 562 |
+
"eval_accuracy": 0.8772935779816514,
|
| 563 |
+
"eval_f1": 0.8158347676419967,
|
| 564 |
+
"eval_loss": 0.2903553247451782,
|
| 565 |
+
"eval_precision": 0.797979797979798,
|
| 566 |
+
"eval_recall": 0.8345070422535211,
|
| 567 |
+
"eval_runtime": 6.7437,
|
| 568 |
+
"eval_samples_per_second": 129.307,
|
| 569 |
+
"step": 165
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.4,
|
| 573 |
+
"learning_rate": 1.1840490797546013e-05,
|
| 574 |
+
"loss": 0.2701,
|
| 575 |
+
"step": 170
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.4,
|
| 579 |
+
"eval_accuracy": 0.8795871559633027,
|
| 580 |
+
"eval_f1": 0.8205128205128205,
|
| 581 |
+
"eval_loss": 0.29034143686294556,
|
| 582 |
+
"eval_precision": 0.7973421926910299,
|
| 583 |
+
"eval_recall": 0.8450704225352113,
|
| 584 |
+
"eval_runtime": 5.3852,
|
| 585 |
+
"eval_samples_per_second": 161.925,
|
| 586 |
+
"step": 170
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.45,
|
| 590 |
+
"learning_rate": 1.1533742331288344e-05,
|
| 591 |
+
"loss": 0.2579,
|
| 592 |
+
"step": 175
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.45,
|
| 596 |
+
"eval_accuracy": 0.8864678899082569,
|
| 597 |
+
"eval_f1": 0.8241563055062167,
|
| 598 |
+
"eval_loss": 0.28575021028518677,
|
| 599 |
+
"eval_precision": 0.8315412186379928,
|
| 600 |
+
"eval_recall": 0.8169014084507042,
|
| 601 |
+
"eval_runtime": 5.1529,
|
| 602 |
+
"eval_samples_per_second": 169.224,
|
| 603 |
+
"step": 175
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.49,
|
| 607 |
+
"learning_rate": 1.1226993865030675e-05,
|
| 608 |
+
"loss": 0.2523,
|
| 609 |
+
"step": 180
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.49,
|
| 613 |
+
"eval_accuracy": 0.8864678899082569,
|
| 614 |
+
"eval_f1": 0.8241563055062167,
|
| 615 |
+
"eval_loss": 0.2819433808326721,
|
| 616 |
+
"eval_precision": 0.8315412186379928,
|
| 617 |
+
"eval_recall": 0.8169014084507042,
|
| 618 |
+
"eval_runtime": 6.7646,
|
| 619 |
+
"eval_samples_per_second": 128.907,
|
| 620 |
+
"step": 180
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.53,
|
| 624 |
+
"learning_rate": 1.0920245398773005e-05,
|
| 625 |
+
"loss": 0.3262,
|
| 626 |
+
"step": 185
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.53,
|
| 630 |
+
"eval_accuracy": 0.8841743119266054,
|
| 631 |
+
"eval_f1": 0.8206039076376554,
|
| 632 |
+
"eval_loss": 0.27894383668899536,
|
| 633 |
+
"eval_precision": 0.8279569892473119,
|
| 634 |
+
"eval_recall": 0.8133802816901409,
|
| 635 |
+
"eval_runtime": 7.2116,
|
| 636 |
+
"eval_samples_per_second": 120.915,
|
| 637 |
+
"step": 185
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.57,
|
| 641 |
+
"learning_rate": 1.061349693251534e-05,
|
| 642 |
+
"loss": 0.2973,
|
| 643 |
+
"step": 190
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.57,
|
| 647 |
+
"eval_accuracy": 0.8795871559633027,
|
| 648 |
+
"eval_f1": 0.8154657293497363,
|
| 649 |
+
"eval_loss": 0.2783905565738678,
|
| 650 |
+
"eval_precision": 0.8140350877192982,
|
| 651 |
+
"eval_recall": 0.8169014084507042,
|
| 652 |
+
"eval_runtime": 7.1139,
|
| 653 |
+
"eval_samples_per_second": 122.577,
|
| 654 |
+
"step": 190
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.61,
|
| 658 |
+
"learning_rate": 1.030674846625767e-05,
|
| 659 |
+
"loss": 0.3122,
|
| 660 |
+
"step": 195
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.61,
|
| 664 |
+
"eval_accuracy": 0.8772935779816514,
|
| 665 |
+
"eval_f1": 0.8112874779541447,
|
| 666 |
+
"eval_loss": 0.28692659735679626,
|
| 667 |
+
"eval_precision": 0.8127208480565371,
|
| 668 |
+
"eval_recall": 0.8098591549295775,
|
| 669 |
+
"eval_runtime": 7.2602,
|
| 670 |
+
"eval_samples_per_second": 120.107,
|
| 671 |
+
"step": 195
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.65,
|
| 675 |
+
"learning_rate": 1e-05,
|
| 676 |
+
"loss": 0.3195,
|
| 677 |
+
"step": 200
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.65,
|
| 681 |
+
"eval_accuracy": 0.8772935779816514,
|
| 682 |
+
"eval_f1": 0.8078994614003591,
|
| 683 |
+
"eval_loss": 0.2904263436794281,
|
| 684 |
+
"eval_precision": 0.8241758241758241,
|
| 685 |
+
"eval_recall": 0.7922535211267606,
|
| 686 |
+
"eval_runtime": 6.5577,
|
| 687 |
+
"eval_samples_per_second": 132.972,
|
| 688 |
+
"step": 200
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.69,
|
| 692 |
+
"learning_rate": 9.693251533742331e-06,
|
| 693 |
+
"loss": 0.2864,
|
| 694 |
+
"step": 205
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.69,
|
| 698 |
+
"eval_accuracy": 0.8669724770642202,
|
| 699 |
+
"eval_f1": 0.8020477815699658,
|
| 700 |
+
"eval_loss": 0.29111164808273315,
|
| 701 |
+
"eval_precision": 0.7781456953642384,
|
| 702 |
+
"eval_recall": 0.8274647887323944,
|
| 703 |
+
"eval_runtime": 5.8177,
|
| 704 |
+
"eval_samples_per_second": 149.888,
|
| 705 |
+
"step": 205
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.74,
|
| 709 |
+
"learning_rate": 9.386503067484664e-06,
|
| 710 |
+
"loss": 0.3185,
|
| 711 |
+
"step": 210
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.74,
|
| 715 |
+
"eval_accuracy": 0.8635321100917431,
|
| 716 |
+
"eval_f1": 0.8006700167504189,
|
| 717 |
+
"eval_loss": 0.29158464074134827,
|
| 718 |
+
"eval_precision": 0.7635782747603834,
|
| 719 |
+
"eval_recall": 0.8415492957746479,
|
| 720 |
+
"eval_runtime": 5.1013,
|
| 721 |
+
"eval_samples_per_second": 170.936,
|
| 722 |
+
"step": 210
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.78,
|
| 726 |
+
"learning_rate": 9.079754601226994e-06,
|
| 727 |
+
"loss": 0.2743,
|
| 728 |
+
"step": 215
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.78,
|
| 732 |
+
"eval_accuracy": 0.8704128440366973,
|
| 733 |
+
"eval_f1": 0.804159445407279,
|
| 734 |
+
"eval_loss": 0.2849805951118469,
|
| 735 |
+
"eval_precision": 0.7918088737201365,
|
| 736 |
+
"eval_recall": 0.8169014084507042,
|
| 737 |
+
"eval_runtime": 6.2932,
|
| 738 |
+
"eval_samples_per_second": 138.562,
|
| 739 |
+
"step": 215
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.82,
|
| 743 |
+
"learning_rate": 8.773006134969327e-06,
|
| 744 |
+
"loss": 0.3158,
|
| 745 |
+
"step": 220
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.82,
|
| 749 |
+
"eval_accuracy": 0.8669724770642202,
|
| 750 |
+
"eval_f1": 0.8110749185667752,
|
| 751 |
+
"eval_loss": 0.301179438829422,
|
| 752 |
+
"eval_precision": 0.7545454545454545,
|
| 753 |
+
"eval_recall": 0.8767605633802817,
|
| 754 |
+
"eval_runtime": 7.2876,
|
| 755 |
+
"eval_samples_per_second": 119.656,
|
| 756 |
+
"step": 220
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.86,
|
| 760 |
+
"learning_rate": 8.466257668711658e-06,
|
| 761 |
+
"loss": 0.2714,
|
| 762 |
+
"step": 225
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.86,
|
| 766 |
+
"eval_accuracy": 0.8853211009174312,
|
| 767 |
+
"eval_f1": 0.8161764705882353,
|
| 768 |
+
"eval_loss": 0.28371983766555786,
|
| 769 |
+
"eval_precision": 0.8538461538461538,
|
| 770 |
+
"eval_recall": 0.7816901408450704,
|
| 771 |
+
"eval_runtime": 7.0861,
|
| 772 |
+
"eval_samples_per_second": 123.058,
|
| 773 |
+
"step": 225
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.9,
|
| 777 |
+
"learning_rate": 8.159509202453988e-06,
|
| 778 |
+
"loss": 0.2978,
|
| 779 |
+
"step": 230
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.9,
|
| 783 |
+
"eval_accuracy": 0.8738532110091743,
|
| 784 |
+
"eval_f1": 0.8141891891891891,
|
| 785 |
+
"eval_loss": 0.2848930060863495,
|
| 786 |
+
"eval_precision": 0.7824675324675324,
|
| 787 |
+
"eval_recall": 0.8485915492957746,
|
| 788 |
+
"eval_runtime": 7.1621,
|
| 789 |
+
"eval_samples_per_second": 121.752,
|
| 790 |
+
"step": 230
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.94,
|
| 794 |
+
"learning_rate": 7.85276073619632e-06,
|
| 795 |
+
"loss": 0.2857,
|
| 796 |
+
"step": 235
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.94,
|
| 800 |
+
"eval_accuracy": 0.8772935779816514,
|
| 801 |
+
"eval_f1": 0.8189509306260575,
|
| 802 |
+
"eval_loss": 0.28239545226097107,
|
| 803 |
+
"eval_precision": 0.7882736156351792,
|
| 804 |
+
"eval_recall": 0.852112676056338,
|
| 805 |
+
"eval_runtime": 6.4537,
|
| 806 |
+
"eval_samples_per_second": 135.115,
|
| 807 |
+
"step": 235
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.98,
|
| 811 |
+
"learning_rate": 7.54601226993865e-06,
|
| 812 |
+
"loss": 0.2669,
|
| 813 |
+
"step": 240
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.98,
|
| 817 |
+
"eval_accuracy": 0.8876146788990825,
|
| 818 |
+
"eval_f1": 0.8150943396226414,
|
| 819 |
+
"eval_loss": 0.29343676567077637,
|
| 820 |
+
"eval_precision": 0.8780487804878049,
|
| 821 |
+
"eval_recall": 0.7605633802816901,
|
| 822 |
+
"eval_runtime": 5.6057,
|
| 823 |
+
"eval_samples_per_second": 155.557,
|
| 824 |
+
"step": 240
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.02,
|
| 828 |
+
"learning_rate": 7.239263803680983e-06,
|
| 829 |
+
"loss": 0.2786,
|
| 830 |
+
"step": 245
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.02,
|
| 834 |
+
"eval_accuracy": 0.8772935779816514,
|
| 835 |
+
"eval_f1": 0.8189509306260575,
|
| 836 |
+
"eval_loss": 0.28877732157707214,
|
| 837 |
+
"eval_precision": 0.7882736156351792,
|
| 838 |
+
"eval_recall": 0.852112676056338,
|
| 839 |
+
"eval_runtime": 5.106,
|
| 840 |
+
"eval_samples_per_second": 170.781,
|
| 841 |
+
"step": 245
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.07,
|
| 845 |
+
"learning_rate": 6.932515337423313e-06,
|
| 846 |
+
"loss": 0.2484,
|
| 847 |
+
"step": 250
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.07,
|
| 851 |
+
"eval_accuracy": 0.8807339449541285,
|
| 852 |
+
"eval_f1": 0.8237288135593219,
|
| 853 |
+
"eval_loss": 0.285278856754303,
|
| 854 |
+
"eval_precision": 0.7941176470588235,
|
| 855 |
+
"eval_recall": 0.8556338028169014,
|
| 856 |
+
"eval_runtime": 5.1204,
|
| 857 |
+
"eval_samples_per_second": 170.3,
|
| 858 |
+
"step": 250
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.11,
|
| 862 |
+
"learning_rate": 6.625766871165644e-06,
|
| 863 |
+
"loss": 0.2006,
|
| 864 |
+
"step": 255
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.11,
|
| 868 |
+
"eval_accuracy": 0.8899082568807339,
|
| 869 |
+
"eval_f1": 0.8241758241758241,
|
| 870 |
+
"eval_loss": 0.2904672622680664,
|
| 871 |
+
"eval_precision": 0.8587786259541985,
|
| 872 |
+
"eval_recall": 0.7922535211267606,
|
| 873 |
+
"eval_runtime": 7.1075,
|
| 874 |
+
"eval_samples_per_second": 122.688,
|
| 875 |
+
"step": 255
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.15,
|
| 879 |
+
"learning_rate": 6.319018404907976e-06,
|
| 880 |
+
"loss": 0.2564,
|
| 881 |
+
"step": 260
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 2.15,
|
| 885 |
+
"eval_accuracy": 0.8807339449541285,
|
| 886 |
+
"eval_f1": 0.8272425249169436,
|
| 887 |
+
"eval_loss": 0.31366848945617676,
|
| 888 |
+
"eval_precision": 0.7830188679245284,
|
| 889 |
+
"eval_recall": 0.8767605633802817,
|
| 890 |
+
"eval_runtime": 7.0515,
|
| 891 |
+
"eval_samples_per_second": 123.661,
|
| 892 |
+
"step": 260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.19,
|
| 896 |
+
"learning_rate": 6.012269938650307e-06,
|
| 897 |
+
"loss": 0.2652,
|
| 898 |
+
"step": 265
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.19,
|
| 902 |
+
"eval_accuracy": 0.8795871559633027,
|
| 903 |
+
"eval_f1": 0.8247078464106845,
|
| 904 |
+
"eval_loss": 0.29686439037323,
|
| 905 |
+
"eval_precision": 0.7841269841269841,
|
| 906 |
+
"eval_recall": 0.8697183098591549,
|
| 907 |
+
"eval_runtime": 7.3289,
|
| 908 |
+
"eval_samples_per_second": 118.981,
|
| 909 |
+
"step": 265
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.23,
|
| 913 |
+
"learning_rate": 5.7055214723926385e-06,
|
| 914 |
+
"loss": 0.2267,
|
| 915 |
+
"step": 270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.23,
|
| 919 |
+
"eval_accuracy": 0.8876146788990825,
|
| 920 |
+
"eval_f1": 0.8256227758007119,
|
| 921 |
+
"eval_loss": 0.2745262682437897,
|
| 922 |
+
"eval_precision": 0.8345323741007195,
|
| 923 |
+
"eval_recall": 0.8169014084507042,
|
| 924 |
+
"eval_runtime": 6.8361,
|
| 925 |
+
"eval_samples_per_second": 127.558,
|
| 926 |
+
"step": 270
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.27,
|
| 930 |
+
"learning_rate": 5.39877300613497e-06,
|
| 931 |
+
"loss": 0.2089,
|
| 932 |
+
"step": 275
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.27,
|
| 936 |
+
"eval_accuracy": 0.8772935779816514,
|
| 937 |
+
"eval_f1": 0.81195079086116,
|
| 938 |
+
"eval_loss": 0.28398409485816956,
|
| 939 |
+
"eval_precision": 0.8105263157894737,
|
| 940 |
+
"eval_recall": 0.8133802816901409,
|
| 941 |
+
"eval_runtime": 5.1533,
|
| 942 |
+
"eval_samples_per_second": 169.213,
|
| 943 |
+
"step": 275
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.31,
|
| 947 |
+
"learning_rate": 5.092024539877301e-06,
|
| 948 |
+
"loss": 0.2417,
|
| 949 |
+
"step": 280
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.31,
|
| 953 |
+
"eval_accuracy": 0.8784403669724771,
|
| 954 |
+
"eval_f1": 0.8239202657807309,
|
| 955 |
+
"eval_loss": 0.30549222230911255,
|
| 956 |
+
"eval_precision": 0.779874213836478,
|
| 957 |
+
"eval_recall": 0.8732394366197183,
|
| 958 |
+
"eval_runtime": 5.0137,
|
| 959 |
+
"eval_samples_per_second": 173.924,
|
| 960 |
+
"step": 280
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.36,
|
| 964 |
+
"learning_rate": 4.785276073619632e-06,
|
| 965 |
+
"loss": 0.1859,
|
| 966 |
+
"step": 285
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.36,
|
| 970 |
+
"eval_accuracy": 0.875,
|
| 971 |
+
"eval_f1": 0.8174204355108877,
|
| 972 |
+
"eval_loss": 0.2901022434234619,
|
| 973 |
+
"eval_precision": 0.7795527156549521,
|
| 974 |
+
"eval_recall": 0.8591549295774648,
|
| 975 |
+
"eval_runtime": 5.0546,
|
| 976 |
+
"eval_samples_per_second": 172.515,
|
| 977 |
+
"step": 285
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.4,
|
| 981 |
+
"learning_rate": 4.478527607361964e-06,
|
| 982 |
+
"loss": 0.162,
|
| 983 |
+
"step": 290
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.4,
|
| 987 |
+
"eval_accuracy": 0.8841743119266054,
|
| 988 |
+
"eval_f1": 0.8186714542190306,
|
| 989 |
+
"eval_loss": 0.2908870279788971,
|
| 990 |
+
"eval_precision": 0.8351648351648352,
|
| 991 |
+
"eval_recall": 0.8028169014084507,
|
| 992 |
+
"eval_runtime": 5.0477,
|
| 993 |
+
"eval_samples_per_second": 172.752,
|
| 994 |
+
"step": 290
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.44,
|
| 998 |
+
"learning_rate": 4.171779141104294e-06,
|
| 999 |
+
"loss": 0.2655,
|
| 1000 |
+
"step": 295
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.44,
|
| 1004 |
+
"eval_accuracy": 0.8853211009174312,
|
| 1005 |
+
"eval_f1": 0.8220640569395018,
|
| 1006 |
+
"eval_loss": 0.2885466516017914,
|
| 1007 |
+
"eval_precision": 0.8309352517985612,
|
| 1008 |
+
"eval_recall": 0.8133802816901409,
|
| 1009 |
+
"eval_runtime": 5.0462,
|
| 1010 |
+
"eval_samples_per_second": 172.803,
|
| 1011 |
+
"step": 295
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.48,
|
| 1015 |
+
"learning_rate": 3.865030674846626e-06,
|
| 1016 |
+
"loss": 0.2198,
|
| 1017 |
+
"step": 300
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.48,
|
| 1021 |
+
"eval_accuracy": 0.8772935779816514,
|
| 1022 |
+
"eval_f1": 0.8183361629881155,
|
| 1023 |
+
"eval_loss": 0.2900920510292053,
|
| 1024 |
+
"eval_precision": 0.7901639344262295,
|
| 1025 |
+
"eval_recall": 0.8485915492957746,
|
| 1026 |
+
"eval_runtime": 5.0183,
|
| 1027 |
+
"eval_samples_per_second": 173.764,
|
| 1028 |
+
"step": 300
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.52,
|
| 1032 |
+
"learning_rate": 3.5582822085889574e-06,
|
| 1033 |
+
"loss": 0.1997,
|
| 1034 |
+
"step": 305
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.52,
|
| 1038 |
+
"eval_accuracy": 0.875,
|
| 1039 |
+
"eval_f1": 0.8174204355108877,
|
| 1040 |
+
"eval_loss": 0.29444408416748047,
|
| 1041 |
+
"eval_precision": 0.7795527156549521,
|
| 1042 |
+
"eval_recall": 0.8591549295774648,
|
| 1043 |
+
"eval_runtime": 4.9821,
|
| 1044 |
+
"eval_samples_per_second": 175.028,
|
| 1045 |
+
"step": 305
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.56,
|
| 1049 |
+
"learning_rate": 3.251533742331289e-06,
|
| 1050 |
+
"loss": 0.2164,
|
| 1051 |
+
"step": 310
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.56,
|
| 1055 |
+
"eval_accuracy": 0.8876146788990825,
|
| 1056 |
+
"eval_f1": 0.8286713286713286,
|
| 1057 |
+
"eval_loss": 0.2741115391254425,
|
| 1058 |
+
"eval_precision": 0.8229166666666666,
|
| 1059 |
+
"eval_recall": 0.8345070422535211,
|
| 1060 |
+
"eval_runtime": 5.0084,
|
| 1061 |
+
"eval_samples_per_second": 174.109,
|
| 1062 |
+
"step": 310
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.6,
|
| 1066 |
+
"learning_rate": 2.94478527607362e-06,
|
| 1067 |
+
"loss": 0.2352,
|
| 1068 |
+
"step": 315
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.6,
|
| 1072 |
+
"eval_accuracy": 0.8922018348623854,
|
| 1073 |
+
"eval_f1": 0.8362369337979093,
|
| 1074 |
+
"eval_loss": 0.2667850852012634,
|
| 1075 |
+
"eval_precision": 0.8275862068965517,
|
| 1076 |
+
"eval_recall": 0.8450704225352113,
|
| 1077 |
+
"eval_runtime": 5.0123,
|
| 1078 |
+
"eval_samples_per_second": 173.972,
|
| 1079 |
+
"step": 315
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.64,
|
| 1083 |
+
"learning_rate": 2.638036809815951e-06,
|
| 1084 |
+
"loss": 0.1848,
|
| 1085 |
+
"step": 320
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 2.64,
|
| 1089 |
+
"eval_accuracy": 0.8853211009174312,
|
| 1090 |
+
"eval_f1": 0.8310810810810811,
|
| 1091 |
+
"eval_loss": 0.2768068015575409,
|
| 1092 |
+
"eval_precision": 0.7987012987012987,
|
| 1093 |
+
"eval_recall": 0.8661971830985915,
|
| 1094 |
+
"eval_runtime": 4.9976,
|
| 1095 |
+
"eval_samples_per_second": 174.484,
|
| 1096 |
+
"step": 320
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.69,
|
| 1100 |
+
"learning_rate": 2.331288343558282e-06,
|
| 1101 |
+
"loss": 0.2405,
|
| 1102 |
+
"step": 325
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.69,
|
| 1106 |
+
"eval_accuracy": 0.8887614678899083,
|
| 1107 |
+
"eval_f1": 0.8324697754749567,
|
| 1108 |
+
"eval_loss": 0.2706994116306305,
|
| 1109 |
+
"eval_precision": 0.8169491525423729,
|
| 1110 |
+
"eval_recall": 0.8485915492957746,
|
| 1111 |
+
"eval_runtime": 4.9789,
|
| 1112 |
+
"eval_samples_per_second": 175.138,
|
| 1113 |
+
"step": 325
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.73,
|
| 1117 |
+
"learning_rate": 2.0245398773006137e-06,
|
| 1118 |
+
"loss": 0.2175,
|
| 1119 |
+
"step": 330
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.73,
|
| 1123 |
+
"eval_accuracy": 0.8956422018348624,
|
| 1124 |
+
"eval_f1": 0.8400702987697716,
|
| 1125 |
+
"eval_loss": 0.2676824629306793,
|
| 1126 |
+
"eval_precision": 0.8385964912280702,
|
| 1127 |
+
"eval_recall": 0.8415492957746479,
|
| 1128 |
+
"eval_runtime": 4.9748,
|
| 1129 |
+
"eval_samples_per_second": 175.283,
|
| 1130 |
+
"step": 330
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.77,
|
| 1134 |
+
"learning_rate": 1.717791411042945e-06,
|
| 1135 |
+
"loss": 0.2392,
|
| 1136 |
+
"step": 335
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.77,
|
| 1140 |
+
"eval_accuracy": 0.8864678899082569,
|
| 1141 |
+
"eval_f1": 0.82960413080895,
|
| 1142 |
+
"eval_loss": 0.2721306383609772,
|
| 1143 |
+
"eval_precision": 0.8114478114478114,
|
| 1144 |
+
"eval_recall": 0.8485915492957746,
|
| 1145 |
+
"eval_runtime": 4.9711,
|
| 1146 |
+
"eval_samples_per_second": 175.412,
|
| 1147 |
+
"step": 335
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.81,
|
| 1151 |
+
"learning_rate": 1.411042944785276e-06,
|
| 1152 |
+
"loss": 0.2155,
|
| 1153 |
+
"step": 340
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.81,
|
| 1157 |
+
"eval_accuracy": 0.8818807339449541,
|
| 1158 |
+
"eval_f1": 0.8263069139966273,
|
| 1159 |
+
"eval_loss": 0.2795032560825348,
|
| 1160 |
+
"eval_precision": 0.7928802588996764,
|
| 1161 |
+
"eval_recall": 0.8626760563380281,
|
| 1162 |
+
"eval_runtime": 4.9888,
|
| 1163 |
+
"eval_samples_per_second": 174.791,
|
| 1164 |
+
"step": 340
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.85,
|
| 1168 |
+
"learning_rate": 1.1042944785276075e-06,
|
| 1169 |
+
"loss": 0.2833,
|
| 1170 |
+
"step": 345
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.85,
|
| 1174 |
+
"eval_accuracy": 0.8818807339449541,
|
| 1175 |
+
"eval_f1": 0.826890756302521,
|
| 1176 |
+
"eval_loss": 0.28040066361427307,
|
| 1177 |
+
"eval_precision": 0.7909967845659164,
|
| 1178 |
+
"eval_recall": 0.8661971830985915,
|
| 1179 |
+
"eval_runtime": 4.9996,
|
| 1180 |
+
"eval_samples_per_second": 174.413,
|
| 1181 |
+
"step": 345
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 2.89,
|
| 1185 |
+
"learning_rate": 7.975460122699387e-07,
|
| 1186 |
+
"loss": 0.2018,
|
| 1187 |
+
"step": 350
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.89,
|
| 1191 |
+
"eval_accuracy": 0.8864678899082569,
|
| 1192 |
+
"eval_f1": 0.82960413080895,
|
| 1193 |
+
"eval_loss": 0.27195218205451965,
|
| 1194 |
+
"eval_precision": 0.8114478114478114,
|
| 1195 |
+
"eval_recall": 0.8485915492957746,
|
| 1196 |
+
"eval_runtime": 4.9745,
|
| 1197 |
+
"eval_samples_per_second": 175.295,
|
| 1198 |
+
"step": 350
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.93,
|
| 1202 |
+
"learning_rate": 4.9079754601227e-07,
|
| 1203 |
+
"loss": 0.2184,
|
| 1204 |
+
"step": 355
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 2.93,
|
| 1208 |
+
"eval_accuracy": 0.8899082568807339,
|
| 1209 |
+
"eval_f1": 0.832752613240418,
|
| 1210 |
+
"eval_loss": 0.26814883947372437,
|
| 1211 |
+
"eval_precision": 0.8241379310344827,
|
| 1212 |
+
"eval_recall": 0.8415492957746479,
|
| 1213 |
+
"eval_runtime": 5.1102,
|
| 1214 |
+
"eval_samples_per_second": 170.638,
|
| 1215 |
+
"step": 355
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.98,
|
| 1219 |
+
"learning_rate": 1.8404907975460125e-07,
|
| 1220 |
+
"loss": 0.2232,
|
| 1221 |
+
"step": 360
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.98,
|
| 1225 |
+
"eval_accuracy": 0.8910550458715596,
|
| 1226 |
+
"eval_f1": 0.8342059336823734,
|
| 1227 |
+
"eval_loss": 0.26773521304130554,
|
| 1228 |
+
"eval_precision": 0.8269896193771626,
|
| 1229 |
+
"eval_recall": 0.8415492957746479,
|
| 1230 |
+
"eval_runtime": 4.9742,
|
| 1231 |
+
"eval_samples_per_second": 175.303,
|
| 1232 |
+
"step": 360
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 3.0,
|
| 1236 |
+
"step": 363,
|
| 1237 |
+
"total_flos": 1.259652372638976e+16,
|
| 1238 |
+
"train_runtime": 1963.3463,
|
| 1239 |
+
"train_samples_per_second": 0.185
|
| 1240 |
+
}
|
| 1241 |
+
],
|
| 1242 |
+
"max_steps": 363,
|
| 1243 |
+
"num_train_epochs": 3,
|
| 1244 |
+
"total_flos": 1.259652372638976e+16,
|
| 1245 |
+
"trial_name": null,
|
| 1246 |
+
"trial_params": null
|
| 1247 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eec0e4bc362aa6cacc51d1f46ec7b1c1670fcc96c27f36fbaebae09cb806bb65
|
| 3 |
+
size 2351
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|