LL
commited on
Commit
·
0af2060
1
Parent(s):
5224bd5
update
Browse files- all_results.json +14 -0
- config.json +57 -0
- eval_results.json +11 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- scores.txt +1 -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 +652 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy_score": 88.24552794753981,
|
| 4 |
+
"eval_f1": 47.28333789206767,
|
| 5 |
+
"eval_loss": 0.42202675342559814,
|
| 6 |
+
"eval_precision": 57.91411042944785,
|
| 7 |
+
"eval_recall": 65.10344827586206,
|
| 8 |
+
"eval_runtime": 8.8774,
|
| 9 |
+
"eval_samples": 1189,
|
| 10 |
+
"eval_samples_per_second": 133.935,
|
| 11 |
+
"train_runtime": 3394.8711,
|
| 12 |
+
"train_samples": 24184,
|
| 13 |
+
"train_samples_per_second": 0.557
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "results/subtask2-roberta-large-3e-5-32-10-evallabels/checkpoint-950",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"finetuning_task": "deft_task2",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6",
|
| 22 |
+
"7": "LABEL_7",
|
| 23 |
+
"8": "LABEL_8",
|
| 24 |
+
"9": "LABEL_9",
|
| 25 |
+
"10": "LABEL_10",
|
| 26 |
+
"11": "LABEL_11",
|
| 27 |
+
"12": "LABEL_12"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 4096,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"LABEL_0": 0,
|
| 33 |
+
"LABEL_1": 1,
|
| 34 |
+
"LABEL_10": 10,
|
| 35 |
+
"LABEL_11": 11,
|
| 36 |
+
"LABEL_12": 12,
|
| 37 |
+
"LABEL_2": 2,
|
| 38 |
+
"LABEL_3": 3,
|
| 39 |
+
"LABEL_4": 4,
|
| 40 |
+
"LABEL_5": 5,
|
| 41 |
+
"LABEL_6": 6,
|
| 42 |
+
"LABEL_7": 7,
|
| 43 |
+
"LABEL_8": 8,
|
| 44 |
+
"LABEL_9": 9
|
| 45 |
+
},
|
| 46 |
+
"layer_norm_eps": 1e-05,
|
| 47 |
+
"max_position_embeddings": 514,
|
| 48 |
+
"model_type": "roberta",
|
| 49 |
+
"num_attention_heads": 16,
|
| 50 |
+
"num_hidden_layers": 24,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"transformers_version": "4.5.0",
|
| 54 |
+
"type_vocab_size": 1,
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"vocab_size": 50265
|
| 57 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy_score": 87.55634902923455,
|
| 4 |
+
"eval_f1": 43.86838413539317,
|
| 5 |
+
"eval_loss": 0.4299115240573883,
|
| 6 |
+
"eval_precision": 57.91505791505791,
|
| 7 |
+
"eval_recall": 67.7710843373494,
|
| 8 |
+
"eval_runtime": 8.9275,
|
| 9 |
+
"eval_samples": 1179,
|
| 10 |
+
"eval_samples_per_second": 132.064
|
| 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 sha256:0de287487eabe6c80fee74f6322aa5793f71c74123987596df452191c2db069a
|
| 3 |
+
size 1417466615
|
scores.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
subtask_2_f1-score_macro: 0.5285653925817485
|
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": 10.0,
|
| 3 |
+
"eval_accuracy_score": 88.24552794753981,
|
| 4 |
+
"eval_f1": 47.28333789206767,
|
| 5 |
+
"eval_loss": 0.42202675342559814,
|
| 6 |
+
"eval_precision": 57.91411042944785,
|
| 7 |
+
"eval_recall": 65.10344827586206,
|
| 8 |
+
"eval_runtime": 8.8774,
|
| 9 |
+
"eval_samples": 1189,
|
| 10 |
+
"eval_samples_per_second": 133.935
|
| 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": 10.0,
|
| 3 |
+
"train_runtime": 3394.8711,
|
| 4 |
+
"train_samples": 24184,
|
| 5 |
+
"train_samples_per_second": 0.557
|
| 6 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,652 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 43.86838413539317,
|
| 3 |
+
"best_model_checkpoint": "results/subtask2-roberta-large-3e-5-32-10-evallabels/checkpoint-950",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 1890,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.26,
|
| 12 |
+
"learning_rate": 7.936507936507936e-06,
|
| 13 |
+
"loss": 1.4415,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.26,
|
| 18 |
+
"eval_accuracy_score": 76.77304173175631,
|
| 19 |
+
"eval_f1": 0.29239766081871343,
|
| 20 |
+
"eval_loss": 0.6649255752563477,
|
| 21 |
+
"eval_precision": 1.2345679012345678,
|
| 22 |
+
"eval_recall": 1.355421686746988,
|
| 23 |
+
"eval_runtime": 8.6446,
|
| 24 |
+
"eval_samples_per_second": 136.386,
|
| 25 |
+
"step": 50
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.53,
|
| 29 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 30 |
+
"loss": 0.6015,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.53,
|
| 35 |
+
"eval_accuracy_score": 85.00781075652756,
|
| 36 |
+
"eval_f1": 7.7752154879329645,
|
| 37 |
+
"eval_loss": 0.44424399733543396,
|
| 38 |
+
"eval_precision": 23.591549295774648,
|
| 39 |
+
"eval_recall": 20.180722891566266,
|
| 40 |
+
"eval_runtime": 8.8048,
|
| 41 |
+
"eval_samples_per_second": 133.905,
|
| 42 |
+
"step": 100
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.79,
|
| 46 |
+
"learning_rate": 2.380952380952381e-05,
|
| 47 |
+
"loss": 0.4787,
|
| 48 |
+
"step": 150
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.79,
|
| 52 |
+
"eval_accuracy_score": 84.93639812541844,
|
| 53 |
+
"eval_f1": 13.33891292959303,
|
| 54 |
+
"eval_loss": 0.42927324771881104,
|
| 55 |
+
"eval_precision": 30.36036036036036,
|
| 56 |
+
"eval_recall": 50.75301204819277,
|
| 57 |
+
"eval_runtime": 8.7806,
|
| 58 |
+
"eval_samples_per_second": 134.274,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.06,
|
| 63 |
+
"learning_rate": 2.980599647266314e-05,
|
| 64 |
+
"loss": 0.4004,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.06,
|
| 69 |
+
"eval_accuracy_score": 86.96273153313993,
|
| 70 |
+
"eval_f1": 22.702533225449525,
|
| 71 |
+
"eval_loss": 0.3721863925457001,
|
| 72 |
+
"eval_precision": 43.04812834224599,
|
| 73 |
+
"eval_recall": 48.493975903614455,
|
| 74 |
+
"eval_runtime": 8.7281,
|
| 75 |
+
"eval_samples_per_second": 135.081,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.32,
|
| 80 |
+
"learning_rate": 2.8924162257495593e-05,
|
| 81 |
+
"loss": 0.3509,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.32,
|
| 86 |
+
"eval_accuracy_score": 85.72193706761884,
|
| 87 |
+
"eval_f1": 30.029422978055926,
|
| 88 |
+
"eval_loss": 0.3999338746070862,
|
| 89 |
+
"eval_precision": 38.4,
|
| 90 |
+
"eval_recall": 57.831325301204814,
|
| 91 |
+
"eval_runtime": 8.8031,
|
| 92 |
+
"eval_samples_per_second": 133.929,
|
| 93 |
+
"step": 250
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.59,
|
| 97 |
+
"learning_rate": 2.8042328042328043e-05,
|
| 98 |
+
"loss": 0.3751,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.59,
|
| 103 |
+
"eval_accuracy_score": 87.88216915866994,
|
| 104 |
+
"eval_f1": 36.06508408748763,
|
| 105 |
+
"eval_loss": 0.33605942130088806,
|
| 106 |
+
"eval_precision": 48.492791612057665,
|
| 107 |
+
"eval_recall": 55.72289156626506,
|
| 108 |
+
"eval_runtime": 8.8234,
|
| 109 |
+
"eval_samples_per_second": 133.622,
|
| 110 |
+
"step": 300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.85,
|
| 114 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 115 |
+
"loss": 0.32,
|
| 116 |
+
"step": 350
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.85,
|
| 120 |
+
"eval_accuracy_score": 87.23499218924347,
|
| 121 |
+
"eval_f1": 38.96036192862586,
|
| 122 |
+
"eval_loss": 0.3504337668418884,
|
| 123 |
+
"eval_precision": 45.92178770949721,
|
| 124 |
+
"eval_recall": 61.897590361445786,
|
| 125 |
+
"eval_runtime": 8.8119,
|
| 126 |
+
"eval_samples_per_second": 133.797,
|
| 127 |
+
"step": 350
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.12,
|
| 131 |
+
"learning_rate": 2.6278659611992947e-05,
|
| 132 |
+
"loss": 0.338,
|
| 133 |
+
"step": 400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.12,
|
| 137 |
+
"eval_accuracy_score": 87.51617942423566,
|
| 138 |
+
"eval_f1": 37.19003385850202,
|
| 139 |
+
"eval_loss": 0.3751635253429413,
|
| 140 |
+
"eval_precision": 47.30473047304731,
|
| 141 |
+
"eval_recall": 64.7590361445783,
|
| 142 |
+
"eval_runtime": 8.8298,
|
| 143 |
+
"eval_samples_per_second": 133.526,
|
| 144 |
+
"step": 400
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.38,
|
| 148 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 149 |
+
"loss": 0.2625,
|
| 150 |
+
"step": 450
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.38,
|
| 154 |
+
"eval_accuracy_score": 87.68578442311984,
|
| 155 |
+
"eval_f1": 33.11482983162181,
|
| 156 |
+
"eval_loss": 0.3540908396244049,
|
| 157 |
+
"eval_precision": 51.25944584382871,
|
| 158 |
+
"eval_recall": 61.295180722891565,
|
| 159 |
+
"eval_runtime": 8.6563,
|
| 160 |
+
"eval_samples_per_second": 136.201,
|
| 161 |
+
"step": 450
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.65,
|
| 165 |
+
"learning_rate": 2.4514991181657847e-05,
|
| 166 |
+
"loss": 0.2718,
|
| 167 |
+
"step": 500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.65,
|
| 171 |
+
"eval_accuracy_score": 88.29279178754742,
|
| 172 |
+
"eval_f1": 32.55245599678572,
|
| 173 |
+
"eval_loss": 0.3684297502040863,
|
| 174 |
+
"eval_precision": 51.84243964421855,
|
| 175 |
+
"eval_recall": 61.44578313253012,
|
| 176 |
+
"eval_runtime": 8.9791,
|
| 177 |
+
"eval_samples_per_second": 131.305,
|
| 178 |
+
"step": 500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.91,
|
| 182 |
+
"learning_rate": 2.36331569664903e-05,
|
| 183 |
+
"loss": 0.2708,
|
| 184 |
+
"step": 550
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.91,
|
| 188 |
+
"eval_accuracy_score": 86.14594956482928,
|
| 189 |
+
"eval_f1": 38.566294416176056,
|
| 190 |
+
"eval_loss": 0.3753862679004669,
|
| 191 |
+
"eval_precision": 51.88571428571429,
|
| 192 |
+
"eval_recall": 68.37349397590361,
|
| 193 |
+
"eval_runtime": 8.8041,
|
| 194 |
+
"eval_samples_per_second": 133.916,
|
| 195 |
+
"step": 550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.17,
|
| 199 |
+
"learning_rate": 2.275132275132275e-05,
|
| 200 |
+
"loss": 0.2305,
|
| 201 |
+
"step": 600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.17,
|
| 205 |
+
"eval_accuracy_score": 88.5918321803169,
|
| 206 |
+
"eval_f1": 39.92203233980172,
|
| 207 |
+
"eval_loss": 0.3945120573043823,
|
| 208 |
+
"eval_precision": 52.08845208845209,
|
| 209 |
+
"eval_recall": 63.85542168674698,
|
| 210 |
+
"eval_runtime": 8.8109,
|
| 211 |
+
"eval_samples_per_second": 133.812,
|
| 212 |
+
"step": 600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.44,
|
| 216 |
+
"learning_rate": 2.1869488536155205e-05,
|
| 217 |
+
"loss": 0.2122,
|
| 218 |
+
"step": 650
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.44,
|
| 222 |
+
"eval_accuracy_score": 88.7034144164249,
|
| 223 |
+
"eval_f1": 37.88744391080894,
|
| 224 |
+
"eval_loss": 0.35788846015930176,
|
| 225 |
+
"eval_precision": 53.2319391634981,
|
| 226 |
+
"eval_recall": 63.25301204819277,
|
| 227 |
+
"eval_runtime": 8.7495,
|
| 228 |
+
"eval_samples_per_second": 134.751,
|
| 229 |
+
"step": 650
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.7,
|
| 233 |
+
"learning_rate": 2.0987654320987655e-05,
|
| 234 |
+
"loss": 0.2126,
|
| 235 |
+
"step": 700
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.7,
|
| 239 |
+
"eval_accuracy_score": 87.35103771479581,
|
| 240 |
+
"eval_f1": 38.094203066236034,
|
| 241 |
+
"eval_loss": 0.37450292706489563,
|
| 242 |
+
"eval_precision": 52.6071842410197,
|
| 243 |
+
"eval_recall": 68.37349397590361,
|
| 244 |
+
"eval_runtime": 8.8823,
|
| 245 |
+
"eval_samples_per_second": 132.736,
|
| 246 |
+
"step": 700
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.97,
|
| 250 |
+
"learning_rate": 2.0105820105820105e-05,
|
| 251 |
+
"loss": 0.211,
|
| 252 |
+
"step": 750
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.97,
|
| 256 |
+
"eval_accuracy_score": 88.2883284981031,
|
| 257 |
+
"eval_f1": 38.51324803050831,
|
| 258 |
+
"eval_loss": 0.3612821102142334,
|
| 259 |
+
"eval_precision": 61.22159090909091,
|
| 260 |
+
"eval_recall": 64.90963855421687,
|
| 261 |
+
"eval_runtime": 9.0113,
|
| 262 |
+
"eval_samples_per_second": 130.836,
|
| 263 |
+
"step": 750
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.23,
|
| 267 |
+
"learning_rate": 1.922398589065256e-05,
|
| 268 |
+
"loss": 0.1651,
|
| 269 |
+
"step": 800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.23,
|
| 273 |
+
"eval_accuracy_score": 88.56505244365097,
|
| 274 |
+
"eval_f1": 38.932898373925724,
|
| 275 |
+
"eval_loss": 0.44898930191993713,
|
| 276 |
+
"eval_precision": 57.75749674054759,
|
| 277 |
+
"eval_recall": 66.71686746987952,
|
| 278 |
+
"eval_runtime": 10.3767,
|
| 279 |
+
"eval_samples_per_second": 113.62,
|
| 280 |
+
"step": 800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.5,
|
| 284 |
+
"learning_rate": 1.834215167548501e-05,
|
| 285 |
+
"loss": 0.1649,
|
| 286 |
+
"step": 850
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.5,
|
| 290 |
+
"eval_accuracy_score": 88.66324481142603,
|
| 291 |
+
"eval_f1": 39.08416734249581,
|
| 292 |
+
"eval_loss": 0.45583415031433105,
|
| 293 |
+
"eval_precision": 58.894878706199464,
|
| 294 |
+
"eval_recall": 65.8132530120482,
|
| 295 |
+
"eval_runtime": 10.0575,
|
| 296 |
+
"eval_samples_per_second": 117.226,
|
| 297 |
+
"step": 850
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.76,
|
| 301 |
+
"learning_rate": 1.746031746031746e-05,
|
| 302 |
+
"loss": 0.1788,
|
| 303 |
+
"step": 900
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.76,
|
| 307 |
+
"eval_accuracy_score": 88.9622852041955,
|
| 308 |
+
"eval_f1": 40.02918919780824,
|
| 309 |
+
"eval_loss": 0.4240648150444031,
|
| 310 |
+
"eval_precision": 60.96866096866097,
|
| 311 |
+
"eval_recall": 64.45783132530121,
|
| 312 |
+
"eval_runtime": 10.0412,
|
| 313 |
+
"eval_samples_per_second": 117.417,
|
| 314 |
+
"step": 900
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.03,
|
| 318 |
+
"learning_rate": 1.6578483245149913e-05,
|
| 319 |
+
"loss": 0.1676,
|
| 320 |
+
"step": 950
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 5.03,
|
| 324 |
+
"eval_accuracy_score": 87.55634902923455,
|
| 325 |
+
"eval_f1": 43.86838413539317,
|
| 326 |
+
"eval_loss": 0.4299115240573883,
|
| 327 |
+
"eval_precision": 57.91505791505791,
|
| 328 |
+
"eval_recall": 67.7710843373494,
|
| 329 |
+
"eval_runtime": 10.0147,
|
| 330 |
+
"eval_samples_per_second": 117.726,
|
| 331 |
+
"step": 950
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 5.29,
|
| 335 |
+
"learning_rate": 1.5696649029982366e-05,
|
| 336 |
+
"loss": 0.1179,
|
| 337 |
+
"step": 1000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 5.29,
|
| 341 |
+
"eval_accuracy_score": 87.20821245257756,
|
| 342 |
+
"eval_f1": 39.553135574552805,
|
| 343 |
+
"eval_loss": 0.49208664894104004,
|
| 344 |
+
"eval_precision": 56.746532156368225,
|
| 345 |
+
"eval_recall": 67.7710843373494,
|
| 346 |
+
"eval_runtime": 10.0407,
|
| 347 |
+
"eval_samples_per_second": 117.423,
|
| 348 |
+
"step": 1000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.56,
|
| 352 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 353 |
+
"loss": 0.1383,
|
| 354 |
+
"step": 1050
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 5.56,
|
| 358 |
+
"eval_accuracy_score": 87.743807185896,
|
| 359 |
+
"eval_f1": 38.8202089054134,
|
| 360 |
+
"eval_loss": 0.4442407786846161,
|
| 361 |
+
"eval_precision": 56.649616368286445,
|
| 362 |
+
"eval_recall": 66.71686746987952,
|
| 363 |
+
"eval_runtime": 9.9651,
|
| 364 |
+
"eval_samples_per_second": 118.313,
|
| 365 |
+
"step": 1050
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.82,
|
| 369 |
+
"learning_rate": 1.3932980599647267e-05,
|
| 370 |
+
"loss": 0.1381,
|
| 371 |
+
"step": 1100
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 5.82,
|
| 375 |
+
"eval_accuracy_score": 86.94487837536265,
|
| 376 |
+
"eval_f1": 38.34834659982452,
|
| 377 |
+
"eval_loss": 0.4821961224079132,
|
| 378 |
+
"eval_precision": 59.24932975871313,
|
| 379 |
+
"eval_recall": 66.56626506024097,
|
| 380 |
+
"eval_runtime": 9.9971,
|
| 381 |
+
"eval_samples_per_second": 117.934,
|
| 382 |
+
"step": 1100
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 6.08,
|
| 386 |
+
"learning_rate": 1.3051146384479719e-05,
|
| 387 |
+
"loss": 0.1308,
|
| 388 |
+
"step": 1150
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 6.08,
|
| 392 |
+
"eval_accuracy_score": 87.83307297478241,
|
| 393 |
+
"eval_f1": 43.06179088429465,
|
| 394 |
+
"eval_loss": 0.5310231447219849,
|
| 395 |
+
"eval_precision": 59.2896174863388,
|
| 396 |
+
"eval_recall": 65.36144578313254,
|
| 397 |
+
"eval_runtime": 10.0333,
|
| 398 |
+
"eval_samples_per_second": 117.508,
|
| 399 |
+
"step": 1150
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 6.35,
|
| 403 |
+
"learning_rate": 1.2169312169312169e-05,
|
| 404 |
+
"loss": 0.1008,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 6.35,
|
| 409 |
+
"eval_accuracy_score": 87.8062932381165,
|
| 410 |
+
"eval_f1": 38.25726977101606,
|
| 411 |
+
"eval_loss": 0.5424754023551941,
|
| 412 |
+
"eval_precision": 55.38277511961722,
|
| 413 |
+
"eval_recall": 69.7289156626506,
|
| 414 |
+
"eval_runtime": 9.9751,
|
| 415 |
+
"eval_samples_per_second": 118.194,
|
| 416 |
+
"step": 1200
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 6.61,
|
| 420 |
+
"learning_rate": 1.1287477954144621e-05,
|
| 421 |
+
"loss": 0.1133,
|
| 422 |
+
"step": 1250
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.61,
|
| 426 |
+
"eval_accuracy_score": 88.02945771033251,
|
| 427 |
+
"eval_f1": 40.50705288524587,
|
| 428 |
+
"eval_loss": 0.505093514919281,
|
| 429 |
+
"eval_precision": 57.824933687002655,
|
| 430 |
+
"eval_recall": 65.66265060240963,
|
| 431 |
+
"eval_runtime": 10.0854,
|
| 432 |
+
"eval_samples_per_second": 116.902,
|
| 433 |
+
"step": 1250
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 6.88,
|
| 437 |
+
"learning_rate": 1.0405643738977073e-05,
|
| 438 |
+
"loss": 0.1167,
|
| 439 |
+
"step": 1300
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 6.88,
|
| 443 |
+
"eval_accuracy_score": 87.98928810533363,
|
| 444 |
+
"eval_f1": 37.904391097050066,
|
| 445 |
+
"eval_loss": 0.4733125865459442,
|
| 446 |
+
"eval_precision": 57.469717362045756,
|
| 447 |
+
"eval_recall": 64.30722891566265,
|
| 448 |
+
"eval_runtime": 8.7518,
|
| 449 |
+
"eval_samples_per_second": 134.716,
|
| 450 |
+
"step": 1300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 7.14,
|
| 454 |
+
"learning_rate": 9.523809523809523e-06,
|
| 455 |
+
"loss": 0.0987,
|
| 456 |
+
"step": 1350
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 7.14,
|
| 460 |
+
"eval_accuracy_score": 87.83753626422673,
|
| 461 |
+
"eval_f1": 37.322003651376725,
|
| 462 |
+
"eval_loss": 0.6008809208869934,
|
| 463 |
+
"eval_precision": 55.66502463054187,
|
| 464 |
+
"eval_recall": 68.07228915662651,
|
| 465 |
+
"eval_runtime": 8.967,
|
| 466 |
+
"eval_samples_per_second": 131.482,
|
| 467 |
+
"step": 1350
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 7.41,
|
| 471 |
+
"learning_rate": 8.641975308641977e-06,
|
| 472 |
+
"loss": 0.0929,
|
| 473 |
+
"step": 1400
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 7.41,
|
| 477 |
+
"eval_accuracy_score": 88.2883284981031,
|
| 478 |
+
"eval_f1": 38.96437550077822,
|
| 479 |
+
"eval_loss": 0.5702655911445618,
|
| 480 |
+
"eval_precision": 58.97771952817824,
|
| 481 |
+
"eval_recall": 67.7710843373494,
|
| 482 |
+
"eval_runtime": 10.9203,
|
| 483 |
+
"eval_samples_per_second": 107.964,
|
| 484 |
+
"step": 1400
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 7.67,
|
| 488 |
+
"learning_rate": 7.760141093474427e-06,
|
| 489 |
+
"loss": 0.0939,
|
| 490 |
+
"step": 1450
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 7.67,
|
| 494 |
+
"eval_accuracy_score": 87.980361526445,
|
| 495 |
+
"eval_f1": 36.57320046638653,
|
| 496 |
+
"eval_loss": 0.5611082315444946,
|
| 497 |
+
"eval_precision": 56.08194622279129,
|
| 498 |
+
"eval_recall": 65.96385542168674,
|
| 499 |
+
"eval_runtime": 11.1802,
|
| 500 |
+
"eval_samples_per_second": 105.454,
|
| 501 |
+
"step": 1450
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 7.94,
|
| 505 |
+
"learning_rate": 6.878306878306878e-06,
|
| 506 |
+
"loss": 0.0976,
|
| 507 |
+
"step": 1500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 7.94,
|
| 511 |
+
"eval_accuracy_score": 88.6364650747601,
|
| 512 |
+
"eval_f1": 37.89298254130058,
|
| 513 |
+
"eval_loss": 0.6237432360649109,
|
| 514 |
+
"eval_precision": 59.53360768175583,
|
| 515 |
+
"eval_recall": 65.36144578313254,
|
| 516 |
+
"eval_runtime": 10.4805,
|
| 517 |
+
"eval_samples_per_second": 112.495,
|
| 518 |
+
"step": 1500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.2,
|
| 522 |
+
"learning_rate": 5.99647266313933e-06,
|
| 523 |
+
"loss": 0.0806,
|
| 524 |
+
"step": 1550
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 8.2,
|
| 528 |
+
"eval_accuracy_score": 86.5654987725954,
|
| 529 |
+
"eval_f1": 36.826891066079725,
|
| 530 |
+
"eval_loss": 0.6972205638885498,
|
| 531 |
+
"eval_precision": 57.01643489254109,
|
| 532 |
+
"eval_recall": 67.92168674698796,
|
| 533 |
+
"eval_runtime": 10.9535,
|
| 534 |
+
"eval_samples_per_second": 107.636,
|
| 535 |
+
"step": 1550
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 8.47,
|
| 539 |
+
"learning_rate": 5.114638447971782e-06,
|
| 540 |
+
"loss": 0.0784,
|
| 541 |
+
"step": 1600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 8.47,
|
| 545 |
+
"eval_accuracy_score": 87.85092613255969,
|
| 546 |
+
"eval_f1": 37.500099347680326,
|
| 547 |
+
"eval_loss": 0.6484220623970032,
|
| 548 |
+
"eval_precision": 58.68983957219251,
|
| 549 |
+
"eval_recall": 66.1144578313253,
|
| 550 |
+
"eval_runtime": 8.8955,
|
| 551 |
+
"eval_samples_per_second": 132.539,
|
| 552 |
+
"step": 1600
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 8.73,
|
| 556 |
+
"learning_rate": 4.232804232804233e-06,
|
| 557 |
+
"loss": 0.0821,
|
| 558 |
+
"step": 1650
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 8.73,
|
| 562 |
+
"eval_accuracy_score": 87.84646284311538,
|
| 563 |
+
"eval_f1": 41.22001286807445,
|
| 564 |
+
"eval_loss": 0.6608390808105469,
|
| 565 |
+
"eval_precision": 58.84718498659517,
|
| 566 |
+
"eval_recall": 66.1144578313253,
|
| 567 |
+
"eval_runtime": 8.8611,
|
| 568 |
+
"eval_samples_per_second": 133.053,
|
| 569 |
+
"step": 1650
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 8.99,
|
| 573 |
+
"learning_rate": 3.3509700176366843e-06,
|
| 574 |
+
"loss": 0.0834,
|
| 575 |
+
"step": 1700
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 8.99,
|
| 579 |
+
"eval_accuracy_score": 87.6768578442312,
|
| 580 |
+
"eval_f1": 40.52561281256491,
|
| 581 |
+
"eval_loss": 0.6585069298744202,
|
| 582 |
+
"eval_precision": 56.80628272251309,
|
| 583 |
+
"eval_recall": 65.36144578313254,
|
| 584 |
+
"eval_runtime": 8.9947,
|
| 585 |
+
"eval_samples_per_second": 131.078,
|
| 586 |
+
"step": 1700
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 9.26,
|
| 590 |
+
"learning_rate": 2.469135802469136e-06,
|
| 591 |
+
"loss": 0.0687,
|
| 592 |
+
"step": 1750
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 9.26,
|
| 596 |
+
"eval_accuracy_score": 87.67239455478688,
|
| 597 |
+
"eval_f1": 41.42806666569158,
|
| 598 |
+
"eval_loss": 0.7016396522521973,
|
| 599 |
+
"eval_precision": 57.929226736566186,
|
| 600 |
+
"eval_recall": 66.56626506024097,
|
| 601 |
+
"eval_runtime": 8.6369,
|
| 602 |
+
"eval_samples_per_second": 136.508,
|
| 603 |
+
"step": 1750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 9.52,
|
| 607 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 608 |
+
"loss": 0.0789,
|
| 609 |
+
"step": 1800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 9.52,
|
| 613 |
+
"eval_accuracy_score": 88.091943762553,
|
| 614 |
+
"eval_f1": 40.693681724146366,
|
| 615 |
+
"eval_loss": 0.6877384781837463,
|
| 616 |
+
"eval_precision": 57.810413885180246,
|
| 617 |
+
"eval_recall": 65.21084337349397,
|
| 618 |
+
"eval_runtime": 8.9265,
|
| 619 |
+
"eval_samples_per_second": 132.079,
|
| 620 |
+
"step": 1800
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 9.79,
|
| 624 |
+
"learning_rate": 7.054673721340388e-07,
|
| 625 |
+
"loss": 0.0634,
|
| 626 |
+
"step": 1850
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 9.79,
|
| 630 |
+
"eval_accuracy_score": 87.85985271144834,
|
| 631 |
+
"eval_f1": 40.37377917369942,
|
| 632 |
+
"eval_loss": 0.7008724212646484,
|
| 633 |
+
"eval_precision": 58.56573705179283,
|
| 634 |
+
"eval_recall": 66.41566265060241,
|
| 635 |
+
"eval_runtime": 8.753,
|
| 636 |
+
"eval_samples_per_second": 134.697,
|
| 637 |
+
"step": 1850
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 10.0,
|
| 641 |
+
"step": 1890,
|
| 642 |
+
"total_flos": 6.580960338659328e+16,
|
| 643 |
+
"train_runtime": 3394.8711,
|
| 644 |
+
"train_samples_per_second": 0.557
|
| 645 |
+
}
|
| 646 |
+
],
|
| 647 |
+
"max_steps": 1890,
|
| 648 |
+
"num_train_epochs": 10,
|
| 649 |
+
"total_flos": 6.580960338659328e+16,
|
| 650 |
+
"trial_name": null,
|
| 651 |
+
"trial_params": null
|
| 652 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1fbf388ba134c6f62e8bb9b002359a2de8f0d19590178099e9cece9ab056b34
|
| 3 |
+
size 2351
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|