Commit
·
13ba46b
1
Parent(s):
ec85235
first model version
Browse files- config.json +60 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1150 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/scibert_scivocab_uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"NerSpanModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"LABEL_0": 0,
|
| 33 |
+
"LABEL_1": 1,
|
| 34 |
+
"LABEL_10": 10,
|
| 35 |
+
"LABEL_11": 11,
|
| 36 |
+
"LABEL_12": 12,
|
| 37 |
+
"LABEL_13": 13,
|
| 38 |
+
"LABEL_14": 14,
|
| 39 |
+
"LABEL_15": 15,
|
| 40 |
+
"LABEL_2": 2,
|
| 41 |
+
"LABEL_3": 3,
|
| 42 |
+
"LABEL_4": 4,
|
| 43 |
+
"LABEL_5": 5,
|
| 44 |
+
"LABEL_6": 6,
|
| 45 |
+
"LABEL_7": 7,
|
| 46 |
+
"LABEL_8": 8,
|
| 47 |
+
"LABEL_9": 9
|
| 48 |
+
},
|
| 49 |
+
"layer_norm_eps": 1e-12,
|
| 50 |
+
"max_position_embeddings": 512,
|
| 51 |
+
"model_type": "bert",
|
| 52 |
+
"num_attention_heads": 12,
|
| 53 |
+
"num_hidden_layers": 12,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"position_embedding_type": "absolute",
|
| 56 |
+
"transformers_version": "4.2.2",
|
| 57 |
+
"type_vocab_size": 2,
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 31090
|
| 60 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eedbf08f938742afe5a40383d72a796a3b37d55487c5bdeaf00625847057f47e
|
| 3 |
+
size 879572305
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fce980c90bc65349ec16ecc0d8281e2a7d3c807e857dfa31f1248b4a1dee473
|
| 3 |
+
size 439812425
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28138d1fb1d0d32f2fda32b243256b015d01cdea709da95a4eab2b151e227ef6
|
| 3 |
+
size 623
|
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_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "allenai/scibert_scivocab_uncased", "do_basic_tokenize": true, "never_split": null}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.954646017198851,
|
| 3 |
+
"best_model_checkpoint": "../out/bio/ner-scibert-spanclass-dice/checkpoints/checkpoint-12150",
|
| 4 |
+
"epoch": 53.76106194690266,
|
| 5 |
+
"global_step": 12150,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.66,
|
| 12 |
+
"learning_rate": 9.977876106194692e-06,
|
| 13 |
+
"loss": 0.8423,
|
| 14 |
+
"step": 150
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.66,
|
| 18 |
+
"eval_loss": 0.8136124014854431,
|
| 19 |
+
"eval_micro_f1": 0.8708517694112636,
|
| 20 |
+
"eval_runtime": 8.6661,
|
| 21 |
+
"eval_samples_per_second": 417.257,
|
| 22 |
+
"step": 150
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.33,
|
| 26 |
+
"learning_rate": 9.95575221238938e-06,
|
| 27 |
+
"loss": 0.7429,
|
| 28 |
+
"step": 300
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.33,
|
| 32 |
+
"eval_loss": 0.7772685289382935,
|
| 33 |
+
"eval_micro_f1": 0.9084623888802797,
|
| 34 |
+
"eval_runtime": 8.674,
|
| 35 |
+
"eval_samples_per_second": 416.877,
|
| 36 |
+
"step": 300
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.99,
|
| 40 |
+
"learning_rate": 9.933628318584071e-06,
|
| 41 |
+
"loss": 0.7013,
|
| 42 |
+
"step": 450
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.99,
|
| 46 |
+
"eval_loss": 0.7601113319396973,
|
| 47 |
+
"eval_micro_f1": 0.9269911499422214,
|
| 48 |
+
"eval_runtime": 9.8502,
|
| 49 |
+
"eval_samples_per_second": 367.098,
|
| 50 |
+
"step": 450
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.65,
|
| 54 |
+
"learning_rate": 9.911504424778762e-06,
|
| 55 |
+
"loss": 0.6802,
|
| 56 |
+
"step": 600
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.65,
|
| 60 |
+
"eval_loss": 0.7511240243911743,
|
| 61 |
+
"eval_micro_f1": 0.9305862826855833,
|
| 62 |
+
"eval_runtime": 8.6885,
|
| 63 |
+
"eval_samples_per_second": 416.182,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.32,
|
| 68 |
+
"learning_rate": 9.889380530973453e-06,
|
| 69 |
+
"loss": 0.6621,
|
| 70 |
+
"step": 750
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 3.32,
|
| 74 |
+
"eval_loss": 0.7457098364830017,
|
| 75 |
+
"eval_micro_f1": 0.9341814154289452,
|
| 76 |
+
"eval_runtime": 8.7277,
|
| 77 |
+
"eval_samples_per_second": 414.315,
|
| 78 |
+
"step": 750
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.98,
|
| 82 |
+
"learning_rate": 9.867256637168142e-06,
|
| 83 |
+
"loss": 0.6506,
|
| 84 |
+
"step": 900
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.98,
|
| 88 |
+
"eval_loss": 0.7396827340126038,
|
| 89 |
+
"eval_micro_f1": 0.9391592915351384,
|
| 90 |
+
"eval_runtime": 9.3794,
|
| 91 |
+
"eval_samples_per_second": 385.525,
|
| 92 |
+
"step": 900
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.65,
|
| 96 |
+
"learning_rate": 9.845132743362832e-06,
|
| 97 |
+
"loss": 0.6494,
|
| 98 |
+
"step": 1050
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.65,
|
| 102 |
+
"eval_loss": 0.7364537119865417,
|
| 103 |
+
"eval_micro_f1": 0.9363938048094755,
|
| 104 |
+
"eval_runtime": 9.3845,
|
| 105 |
+
"eval_samples_per_second": 385.315,
|
| 106 |
+
"step": 1050
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 5.31,
|
| 110 |
+
"learning_rate": 9.823008849557523e-06,
|
| 111 |
+
"loss": 0.6381,
|
| 112 |
+
"step": 1200
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 5.31,
|
| 116 |
+
"eval_loss": 0.7324703335762024,
|
| 117 |
+
"eval_micro_f1": 0.9416482295882351,
|
| 118 |
+
"eval_runtime": 9.4893,
|
| 119 |
+
"eval_samples_per_second": 381.062,
|
| 120 |
+
"step": 1200
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.97,
|
| 124 |
+
"learning_rate": 9.800884955752214e-06,
|
| 125 |
+
"loss": 0.6266,
|
| 126 |
+
"step": 1350
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.97,
|
| 130 |
+
"eval_loss": 0.7316550016403198,
|
| 131 |
+
"eval_micro_f1": 0.9347345127740777,
|
| 132 |
+
"eval_runtime": 9.5002,
|
| 133 |
+
"eval_samples_per_second": 380.623,
|
| 134 |
+
"step": 1350
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.64,
|
| 138 |
+
"learning_rate": 9.778761061946903e-06,
|
| 139 |
+
"loss": 0.626,
|
| 140 |
+
"step": 1500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.64,
|
| 144 |
+
"eval_loss": 0.7285893559455872,
|
| 145 |
+
"eval_micro_f1": 0.9441371676413318,
|
| 146 |
+
"eval_runtime": 8.8611,
|
| 147 |
+
"eval_samples_per_second": 408.077,
|
| 148 |
+
"step": 1500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.3,
|
| 152 |
+
"learning_rate": 9.756637168141593e-06,
|
| 153 |
+
"loss": 0.6256,
|
| 154 |
+
"step": 1650
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 7.3,
|
| 158 |
+
"eval_loss": 0.7262205481529236,
|
| 159 |
+
"eval_micro_f1": 0.9491150437475251,
|
| 160 |
+
"eval_runtime": 9.627,
|
| 161 |
+
"eval_samples_per_second": 375.609,
|
| 162 |
+
"step": 1650
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.96,
|
| 166 |
+
"learning_rate": 9.734513274336284e-06,
|
| 167 |
+
"loss": 0.6227,
|
| 168 |
+
"step": 1800
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.96,
|
| 172 |
+
"eval_loss": 0.7256479859352112,
|
| 173 |
+
"eval_micro_f1": 0.9485619464023926,
|
| 174 |
+
"eval_runtime": 9.26,
|
| 175 |
+
"eval_samples_per_second": 390.497,
|
| 176 |
+
"step": 1800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.63,
|
| 180 |
+
"learning_rate": 9.712389380530975e-06,
|
| 181 |
+
"loss": 0.6212,
|
| 182 |
+
"step": 1950
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.63,
|
| 186 |
+
"eval_loss": 0.7240573763847351,
|
| 187 |
+
"eval_micro_f1": 0.9485619464023926,
|
| 188 |
+
"eval_runtime": 9.5068,
|
| 189 |
+
"eval_samples_per_second": 380.358,
|
| 190 |
+
"step": 1950
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 9.29,
|
| 194 |
+
"learning_rate": 9.690265486725664e-06,
|
| 195 |
+
"loss": 0.6139,
|
| 196 |
+
"step": 2100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 9.29,
|
| 200 |
+
"eval_loss": 0.723069965839386,
|
| 201 |
+
"eval_micro_f1": 0.9466261056944284,
|
| 202 |
+
"eval_runtime": 9.5375,
|
| 203 |
+
"eval_samples_per_second": 379.133,
|
| 204 |
+
"step": 2100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 9.96,
|
| 208 |
+
"learning_rate": 9.668141592920355e-06,
|
| 209 |
+
"loss": 0.6171,
|
| 210 |
+
"step": 2250
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 9.96,
|
| 214 |
+
"eval_loss": 0.7234218716621399,
|
| 215 |
+
"eval_micro_f1": 0.9496681410926577,
|
| 216 |
+
"eval_runtime": 9.3125,
|
| 217 |
+
"eval_samples_per_second": 388.295,
|
| 218 |
+
"step": 2250
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 10.62,
|
| 222 |
+
"learning_rate": 9.646017699115045e-06,
|
| 223 |
+
"loss": 0.6093,
|
| 224 |
+
"step": 2400
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 10.62,
|
| 228 |
+
"eval_loss": 0.7221475839614868,
|
| 229 |
+
"eval_micro_f1": 0.9469026543669947,
|
| 230 |
+
"eval_runtime": 9.5515,
|
| 231 |
+
"eval_samples_per_second": 378.58,
|
| 232 |
+
"step": 2400
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 11.28,
|
| 236 |
+
"learning_rate": 9.623893805309736e-06,
|
| 237 |
+
"loss": 0.6078,
|
| 238 |
+
"step": 2550
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 11.28,
|
| 242 |
+
"eval_loss": 0.7231661081314087,
|
| 243 |
+
"eval_micro_f1": 0.947179203039561,
|
| 244 |
+
"eval_runtime": 9.4735,
|
| 245 |
+
"eval_samples_per_second": 381.697,
|
| 246 |
+
"step": 2550
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 11.95,
|
| 250 |
+
"learning_rate": 9.601769911504427e-06,
|
| 251 |
+
"loss": 0.6122,
|
| 252 |
+
"step": 2700
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 11.95,
|
| 256 |
+
"eval_loss": 0.7217335104942322,
|
| 257 |
+
"eval_micro_f1": 0.9446902649864644,
|
| 258 |
+
"eval_runtime": 9.4638,
|
| 259 |
+
"eval_samples_per_second": 382.089,
|
| 260 |
+
"step": 2700
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 12.61,
|
| 264 |
+
"learning_rate": 9.579646017699116e-06,
|
| 265 |
+
"loss": 0.612,
|
| 266 |
+
"step": 2850
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 12.61,
|
| 270 |
+
"eval_loss": 0.7212682366371155,
|
| 271 |
+
"eval_micro_f1": 0.9466261056944284,
|
| 272 |
+
"eval_runtime": 9.4758,
|
| 273 |
+
"eval_samples_per_second": 381.603,
|
| 274 |
+
"step": 2850
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 13.27,
|
| 278 |
+
"learning_rate": 9.557522123893806e-06,
|
| 279 |
+
"loss": 0.6134,
|
| 280 |
+
"step": 3000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.27,
|
| 284 |
+
"eval_loss": 0.7197656035423279,
|
| 285 |
+
"eval_micro_f1": 0.9474557517121274,
|
| 286 |
+
"eval_runtime": 9.1216,
|
| 287 |
+
"eval_samples_per_second": 396.422,
|
| 288 |
+
"step": 3000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 13.94,
|
| 292 |
+
"learning_rate": 9.535398230088495e-06,
|
| 293 |
+
"loss": 0.607,
|
| 294 |
+
"step": 3150
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 13.94,
|
| 298 |
+
"eval_loss": 0.7211037278175354,
|
| 299 |
+
"eval_micro_f1": 0.9430309729510666,
|
| 300 |
+
"eval_runtime": 9.5003,
|
| 301 |
+
"eval_samples_per_second": 380.62,
|
| 302 |
+
"step": 3150
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 14.6,
|
| 306 |
+
"learning_rate": 9.513274336283188e-06,
|
| 307 |
+
"loss": 0.6023,
|
| 308 |
+
"step": 3300
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 14.6,
|
| 312 |
+
"eval_loss": 0.7198509573936462,
|
| 313 |
+
"eval_micro_f1": 0.9477323003846936,
|
| 314 |
+
"eval_runtime": 9.7084,
|
| 315 |
+
"eval_samples_per_second": 372.461,
|
| 316 |
+
"step": 3300
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 15.27,
|
| 320 |
+
"learning_rate": 9.491150442477877e-06,
|
| 321 |
+
"loss": 0.6084,
|
| 322 |
+
"step": 3450
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 15.27,
|
| 326 |
+
"eval_loss": 0.7201675772666931,
|
| 327 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 328 |
+
"eval_runtime": 8.7893,
|
| 329 |
+
"eval_samples_per_second": 411.412,
|
| 330 |
+
"step": 3450
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 15.93,
|
| 334 |
+
"learning_rate": 9.469026548672568e-06,
|
| 335 |
+
"loss": 0.6111,
|
| 336 |
+
"step": 3600
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 15.93,
|
| 340 |
+
"eval_loss": 0.7195026874542236,
|
| 341 |
+
"eval_micro_f1": 0.9463495570218622,
|
| 342 |
+
"eval_runtime": 9.5062,
|
| 343 |
+
"eval_samples_per_second": 380.382,
|
| 344 |
+
"step": 3600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 16.59,
|
| 348 |
+
"learning_rate": 9.446902654867257e-06,
|
| 349 |
+
"loss": 0.5994,
|
| 350 |
+
"step": 3750
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 16.59,
|
| 354 |
+
"eval_loss": 0.7199171185493469,
|
| 355 |
+
"eval_micro_f1": 0.9449668136590308,
|
| 356 |
+
"eval_runtime": 9.3322,
|
| 357 |
+
"eval_samples_per_second": 387.476,
|
| 358 |
+
"step": 3750
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 17.26,
|
| 362 |
+
"learning_rate": 9.424778761061947e-06,
|
| 363 |
+
"loss": 0.6087,
|
| 364 |
+
"step": 3900
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 17.26,
|
| 368 |
+
"eval_loss": 0.7187968492507935,
|
| 369 |
+
"eval_micro_f1": 0.9477323003846936,
|
| 370 |
+
"eval_runtime": 10.5814,
|
| 371 |
+
"eval_samples_per_second": 341.733,
|
| 372 |
+
"step": 3900
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 17.92,
|
| 376 |
+
"learning_rate": 9.402654867256638e-06,
|
| 377 |
+
"loss": 0.604,
|
| 378 |
+
"step": 4050
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 17.92,
|
| 382 |
+
"eval_loss": 0.7195943593978882,
|
| 383 |
+
"eval_micro_f1": 0.9435840702961992,
|
| 384 |
+
"eval_runtime": 9.4668,
|
| 385 |
+
"eval_samples_per_second": 381.967,
|
| 386 |
+
"step": 4050
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 18.58,
|
| 390 |
+
"learning_rate": 9.380530973451329e-06,
|
| 391 |
+
"loss": 0.6044,
|
| 392 |
+
"step": 4200
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 18.58,
|
| 396 |
+
"eval_loss": 0.718863844871521,
|
| 397 |
+
"eval_micro_f1": 0.9358407074643429,
|
| 398 |
+
"eval_runtime": 8.7769,
|
| 399 |
+
"eval_samples_per_second": 411.992,
|
| 400 |
+
"step": 4200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 19.25,
|
| 404 |
+
"learning_rate": 9.358407079646018e-06,
|
| 405 |
+
"loss": 0.6096,
|
| 406 |
+
"step": 4350
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 19.25,
|
| 410 |
+
"eval_loss": 0.7180087566375732,
|
| 411 |
+
"eval_micro_f1": 0.9438606189687655,
|
| 412 |
+
"eval_runtime": 9.581,
|
| 413 |
+
"eval_samples_per_second": 377.415,
|
| 414 |
+
"step": 4350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 19.91,
|
| 418 |
+
"learning_rate": 9.336283185840708e-06,
|
| 419 |
+
"loss": 0.6046,
|
| 420 |
+
"step": 4500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 19.91,
|
| 424 |
+
"eval_loss": 0.7181408405303955,
|
| 425 |
+
"eval_micro_f1": 0.9457964596767295,
|
| 426 |
+
"eval_runtime": 9.2502,
|
| 427 |
+
"eval_samples_per_second": 390.908,
|
| 428 |
+
"step": 4500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 20.58,
|
| 432 |
+
"learning_rate": 9.314159292035399e-06,
|
| 433 |
+
"loss": 0.6028,
|
| 434 |
+
"step": 4650
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 20.58,
|
| 438 |
+
"eval_loss": 0.7181771397590637,
|
| 439 |
+
"eval_micro_f1": 0.9496681410926577,
|
| 440 |
+
"eval_runtime": 9.4887,
|
| 441 |
+
"eval_samples_per_second": 381.084,
|
| 442 |
+
"step": 4650
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 21.24,
|
| 446 |
+
"learning_rate": 9.29203539823009e-06,
|
| 447 |
+
"loss": 0.6066,
|
| 448 |
+
"step": 4800
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 21.24,
|
| 452 |
+
"eval_loss": 0.7180553674697876,
|
| 453 |
+
"eval_micro_f1": 0.9496681410926577,
|
| 454 |
+
"eval_runtime": 9.5643,
|
| 455 |
+
"eval_samples_per_second": 378.074,
|
| 456 |
+
"step": 4800
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 21.9,
|
| 460 |
+
"learning_rate": 9.26991150442478e-06,
|
| 461 |
+
"loss": 0.5981,
|
| 462 |
+
"step": 4950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 21.9,
|
| 466 |
+
"eval_loss": 0.7184288501739502,
|
| 467 |
+
"eval_micro_f1": 0.9474557517121274,
|
| 468 |
+
"eval_runtime": 9.5293,
|
| 469 |
+
"eval_samples_per_second": 379.463,
|
| 470 |
+
"step": 4950
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 22.57,
|
| 474 |
+
"learning_rate": 9.24778761061947e-06,
|
| 475 |
+
"loss": 0.6051,
|
| 476 |
+
"step": 5100
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 22.57,
|
| 480 |
+
"eval_loss": 0.7198731899261475,
|
| 481 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 482 |
+
"eval_runtime": 9.5484,
|
| 483 |
+
"eval_samples_per_second": 378.701,
|
| 484 |
+
"step": 5100
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 23.23,
|
| 488 |
+
"learning_rate": 9.22566371681416e-06,
|
| 489 |
+
"loss": 0.606,
|
| 490 |
+
"step": 5250
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 23.23,
|
| 494 |
+
"eval_loss": 0.719587504863739,
|
| 495 |
+
"eval_micro_f1": 0.9480088490572599,
|
| 496 |
+
"eval_runtime": 9.1658,
|
| 497 |
+
"eval_samples_per_second": 394.511,
|
| 498 |
+
"step": 5250
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 23.89,
|
| 502 |
+
"learning_rate": 9.203539823008851e-06,
|
| 503 |
+
"loss": 0.6026,
|
| 504 |
+
"step": 5400
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 23.89,
|
| 508 |
+
"eval_loss": 0.7177981734275818,
|
| 509 |
+
"eval_micro_f1": 0.9457964596767295,
|
| 510 |
+
"eval_runtime": 9.4924,
|
| 511 |
+
"eval_samples_per_second": 380.936,
|
| 512 |
+
"step": 5400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 24.56,
|
| 516 |
+
"learning_rate": 9.181415929203542e-06,
|
| 517 |
+
"loss": 0.6056,
|
| 518 |
+
"step": 5550
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 24.56,
|
| 522 |
+
"eval_loss": 0.7172006368637085,
|
| 523 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 524 |
+
"eval_runtime": 9.5788,
|
| 525 |
+
"eval_samples_per_second": 377.498,
|
| 526 |
+
"step": 5550
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 25.22,
|
| 530 |
+
"learning_rate": 9.15929203539823e-06,
|
| 531 |
+
"loss": 0.6055,
|
| 532 |
+
"step": 5700
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 25.22,
|
| 536 |
+
"eval_loss": 0.7203790545463562,
|
| 537 |
+
"eval_micro_f1": 0.9402654862254036,
|
| 538 |
+
"eval_runtime": 8.7723,
|
| 539 |
+
"eval_samples_per_second": 412.206,
|
| 540 |
+
"step": 5700
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 25.88,
|
| 544 |
+
"learning_rate": 9.137168141592921e-06,
|
| 545 |
+
"loss": 0.5973,
|
| 546 |
+
"step": 5850
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 25.88,
|
| 550 |
+
"eval_loss": 0.7177384495735168,
|
| 551 |
+
"eval_micro_f1": 0.9513274331280555,
|
| 552 |
+
"eval_runtime": 9.578,
|
| 553 |
+
"eval_samples_per_second": 377.534,
|
| 554 |
+
"step": 5850
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 26.55,
|
| 558 |
+
"learning_rate": 9.11504424778761e-06,
|
| 559 |
+
"loss": 0.6076,
|
| 560 |
+
"step": 6000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 26.55,
|
| 564 |
+
"eval_loss": 0.7195953130722046,
|
| 565 |
+
"eval_micro_f1": 0.9433075216236328,
|
| 566 |
+
"eval_runtime": 10.5304,
|
| 567 |
+
"eval_samples_per_second": 343.388,
|
| 568 |
+
"step": 6000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 27.21,
|
| 572 |
+
"learning_rate": 9.092920353982303e-06,
|
| 573 |
+
"loss": 0.6037,
|
| 574 |
+
"step": 6150
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 27.21,
|
| 578 |
+
"eval_loss": 0.7189124226570129,
|
| 579 |
+
"eval_micro_f1": 0.945243362331597,
|
| 580 |
+
"eval_runtime": 9.5745,
|
| 581 |
+
"eval_samples_per_second": 377.668,
|
| 582 |
+
"step": 6150
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 27.88,
|
| 586 |
+
"learning_rate": 9.070796460176992e-06,
|
| 587 |
+
"loss": 0.6002,
|
| 588 |
+
"step": 6300
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 27.88,
|
| 592 |
+
"eval_loss": 0.7183624505996704,
|
| 593 |
+
"eval_micro_f1": 0.9422013269333677,
|
| 594 |
+
"eval_runtime": 9.5247,
|
| 595 |
+
"eval_samples_per_second": 379.646,
|
| 596 |
+
"step": 6300
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 28.54,
|
| 600 |
+
"learning_rate": 9.048672566371682e-06,
|
| 601 |
+
"loss": 0.5995,
|
| 602 |
+
"step": 6450
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 28.54,
|
| 606 |
+
"eval_loss": 0.7185026407241821,
|
| 607 |
+
"eval_micro_f1": 0.945243362331597,
|
| 608 |
+
"eval_runtime": 8.8185,
|
| 609 |
+
"eval_samples_per_second": 410.046,
|
| 610 |
+
"step": 6450
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 29.2,
|
| 614 |
+
"learning_rate": 9.026548672566371e-06,
|
| 615 |
+
"loss": 0.6088,
|
| 616 |
+
"step": 6600
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 29.2,
|
| 620 |
+
"eval_loss": 0.7188266515731812,
|
| 621 |
+
"eval_micro_f1": 0.9419247782608015,
|
| 622 |
+
"eval_runtime": 9.6772,
|
| 623 |
+
"eval_samples_per_second": 373.662,
|
| 624 |
+
"step": 6600
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 29.87,
|
| 628 |
+
"learning_rate": 9.004424778761062e-06,
|
| 629 |
+
"loss": 0.602,
|
| 630 |
+
"step": 6750
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 29.87,
|
| 634 |
+
"eval_loss": 0.7173834443092346,
|
| 635 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 636 |
+
"eval_runtime": 9.3753,
|
| 637 |
+
"eval_samples_per_second": 385.695,
|
| 638 |
+
"step": 6750
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 30.53,
|
| 642 |
+
"learning_rate": 8.982300884955753e-06,
|
| 643 |
+
"loss": 0.6057,
|
| 644 |
+
"step": 6900
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 30.53,
|
| 648 |
+
"eval_loss": 0.719177782535553,
|
| 649 |
+
"eval_micro_f1": 0.9474557517121274,
|
| 650 |
+
"eval_runtime": 9.5982,
|
| 651 |
+
"eval_samples_per_second": 376.736,
|
| 652 |
+
"step": 6900
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 31.19,
|
| 656 |
+
"learning_rate": 8.960176991150443e-06,
|
| 657 |
+
"loss": 0.604,
|
| 658 |
+
"step": 7050
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 31.19,
|
| 662 |
+
"eval_loss": 0.7192238569259644,
|
| 663 |
+
"eval_micro_f1": 0.9416482295882351,
|
| 664 |
+
"eval_runtime": 9.6495,
|
| 665 |
+
"eval_samples_per_second": 374.736,
|
| 666 |
+
"step": 7050
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 31.86,
|
| 670 |
+
"learning_rate": 8.938053097345133e-06,
|
| 671 |
+
"loss": 0.6062,
|
| 672 |
+
"step": 7200
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 31.86,
|
| 676 |
+
"eval_loss": 0.7208277583122253,
|
| 677 |
+
"eval_micro_f1": 0.9358407074643429,
|
| 678 |
+
"eval_runtime": 8.8172,
|
| 679 |
+
"eval_samples_per_second": 410.106,
|
| 680 |
+
"step": 7200
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 32.52,
|
| 684 |
+
"learning_rate": 8.915929203539823e-06,
|
| 685 |
+
"loss": 0.5952,
|
| 686 |
+
"step": 7350
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 32.52,
|
| 690 |
+
"eval_loss": 0.7197518944740295,
|
| 691 |
+
"eval_micro_f1": 0.94054203489797,
|
| 692 |
+
"eval_runtime": 9.5177,
|
| 693 |
+
"eval_samples_per_second": 379.925,
|
| 694 |
+
"step": 7350
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 33.19,
|
| 698 |
+
"learning_rate": 8.893805309734514e-06,
|
| 699 |
+
"loss": 0.6097,
|
| 700 |
+
"step": 7500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 33.19,
|
| 704 |
+
"eval_loss": 0.7175168991088867,
|
| 705 |
+
"eval_micro_f1": 0.9466261056944284,
|
| 706 |
+
"eval_runtime": 9.6701,
|
| 707 |
+
"eval_samples_per_second": 373.936,
|
| 708 |
+
"step": 7500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 33.85,
|
| 712 |
+
"learning_rate": 8.871681415929205e-06,
|
| 713 |
+
"loss": 0.6022,
|
| 714 |
+
"step": 7650
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 33.85,
|
| 718 |
+
"eval_loss": 0.716774046421051,
|
| 719 |
+
"eval_micro_f1": 0.9474557517121274,
|
| 720 |
+
"eval_runtime": 9.597,
|
| 721 |
+
"eval_samples_per_second": 376.786,
|
| 722 |
+
"step": 7650
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 34.51,
|
| 726 |
+
"learning_rate": 8.849557522123895e-06,
|
| 727 |
+
"loss": 0.6036,
|
| 728 |
+
"step": 7800
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 34.51,
|
| 732 |
+
"eval_loss": 0.716645359992981,
|
| 733 |
+
"eval_micro_f1": 0.9510508844554891,
|
| 734 |
+
"eval_runtime": 9.6812,
|
| 735 |
+
"eval_samples_per_second": 373.509,
|
| 736 |
+
"step": 7800
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 35.18,
|
| 740 |
+
"learning_rate": 8.827433628318584e-06,
|
| 741 |
+
"loss": 0.6032,
|
| 742 |
+
"step": 7950
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 35.18,
|
| 746 |
+
"eval_loss": 0.7164170742034912,
|
| 747 |
+
"eval_micro_f1": 0.9504977871103566,
|
| 748 |
+
"eval_runtime": 8.7651,
|
| 749 |
+
"eval_samples_per_second": 412.544,
|
| 750 |
+
"step": 7950
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 35.84,
|
| 754 |
+
"learning_rate": 8.805309734513275e-06,
|
| 755 |
+
"loss": 0.6009,
|
| 756 |
+
"step": 8100
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 35.84,
|
| 760 |
+
"eval_loss": 0.7191314697265625,
|
| 761 |
+
"eval_micro_f1": 0.9413716809156688,
|
| 762 |
+
"eval_runtime": 9.5325,
|
| 763 |
+
"eval_samples_per_second": 379.332,
|
| 764 |
+
"step": 8100
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 36.5,
|
| 768 |
+
"learning_rate": 8.783185840707966e-06,
|
| 769 |
+
"loss": 0.6038,
|
| 770 |
+
"step": 8250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 36.5,
|
| 774 |
+
"eval_loss": 0.7175291776657104,
|
| 775 |
+
"eval_micro_f1": 0.9463495570218622,
|
| 776 |
+
"eval_runtime": 9.3583,
|
| 777 |
+
"eval_samples_per_second": 386.397,
|
| 778 |
+
"step": 8250
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 37.17,
|
| 782 |
+
"learning_rate": 8.761061946902656e-06,
|
| 783 |
+
"loss": 0.6014,
|
| 784 |
+
"step": 8400
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 37.17,
|
| 788 |
+
"eval_loss": 0.7180671095848083,
|
| 789 |
+
"eval_micro_f1": 0.9449668136590308,
|
| 790 |
+
"eval_runtime": 9.5558,
|
| 791 |
+
"eval_samples_per_second": 378.41,
|
| 792 |
+
"step": 8400
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 37.83,
|
| 796 |
+
"learning_rate": 8.738938053097345e-06,
|
| 797 |
+
"loss": 0.6038,
|
| 798 |
+
"step": 8550
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 37.83,
|
| 802 |
+
"eval_loss": 0.716873049736023,
|
| 803 |
+
"eval_micro_f1": 0.9504977871103566,
|
| 804 |
+
"eval_runtime": 9.4915,
|
| 805 |
+
"eval_samples_per_second": 380.972,
|
| 806 |
+
"step": 8550
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 38.5,
|
| 810 |
+
"learning_rate": 8.716814159292036e-06,
|
| 811 |
+
"loss": 0.6009,
|
| 812 |
+
"step": 8700
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 38.5,
|
| 816 |
+
"eval_loss": 0.7172227501869202,
|
| 817 |
+
"eval_micro_f1": 0.9422013269333677,
|
| 818 |
+
"eval_runtime": 9.542,
|
| 819 |
+
"eval_samples_per_second": 378.955,
|
| 820 |
+
"step": 8700
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 39.16,
|
| 824 |
+
"learning_rate": 8.694690265486727e-06,
|
| 825 |
+
"loss": 0.5999,
|
| 826 |
+
"step": 8850
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 39.16,
|
| 830 |
+
"eval_loss": 0.7166829109191895,
|
| 831 |
+
"eval_micro_f1": 0.9496681410926577,
|
| 832 |
+
"eval_runtime": 10.747,
|
| 833 |
+
"eval_samples_per_second": 336.465,
|
| 834 |
+
"step": 8850
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 39.82,
|
| 838 |
+
"learning_rate": 8.672566371681418e-06,
|
| 839 |
+
"loss": 0.6019,
|
| 840 |
+
"step": 9000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 39.82,
|
| 844 |
+
"eval_loss": 0.7165006399154663,
|
| 845 |
+
"eval_micro_f1": 0.9502212384377903,
|
| 846 |
+
"eval_runtime": 9.5714,
|
| 847 |
+
"eval_samples_per_second": 377.793,
|
| 848 |
+
"step": 9000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 40.49,
|
| 852 |
+
"learning_rate": 8.650442477876107e-06,
|
| 853 |
+
"loss": 0.6037,
|
| 854 |
+
"step": 9150
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 40.49,
|
| 858 |
+
"eval_loss": 0.7166875004768372,
|
| 859 |
+
"eval_micro_f1": 0.945243362331597,
|
| 860 |
+
"eval_runtime": 9.6208,
|
| 861 |
+
"eval_samples_per_second": 375.854,
|
| 862 |
+
"step": 9150
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 41.15,
|
| 866 |
+
"learning_rate": 8.628318584070797e-06,
|
| 867 |
+
"loss": 0.605,
|
| 868 |
+
"step": 9300
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 41.15,
|
| 872 |
+
"eval_loss": 0.7164918184280396,
|
| 873 |
+
"eval_micro_f1": 0.9463495570218622,
|
| 874 |
+
"eval_runtime": 9.5729,
|
| 875 |
+
"eval_samples_per_second": 377.733,
|
| 876 |
+
"step": 9300
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 41.81,
|
| 880 |
+
"learning_rate": 8.606194690265486e-06,
|
| 881 |
+
"loss": 0.5997,
|
| 882 |
+
"step": 9450
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 41.81,
|
| 886 |
+
"eval_loss": 0.7189673781394958,
|
| 887 |
+
"eval_micro_f1": 0.9433075216236328,
|
| 888 |
+
"eval_runtime": 8.8106,
|
| 889 |
+
"eval_samples_per_second": 410.413,
|
| 890 |
+
"step": 9450
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 42.48,
|
| 894 |
+
"learning_rate": 8.584070796460177e-06,
|
| 895 |
+
"loss": 0.6024,
|
| 896 |
+
"step": 9600
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 42.48,
|
| 900 |
+
"eval_loss": 0.7176528573036194,
|
| 901 |
+
"eval_micro_f1": 0.9435840702961992,
|
| 902 |
+
"eval_runtime": 9.5036,
|
| 903 |
+
"eval_samples_per_second": 380.489,
|
| 904 |
+
"step": 9600
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 43.14,
|
| 908 |
+
"learning_rate": 8.561946902654868e-06,
|
| 909 |
+
"loss": 0.6004,
|
| 910 |
+
"step": 9750
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 43.14,
|
| 914 |
+
"eval_loss": 0.7176242470741272,
|
| 915 |
+
"eval_micro_f1": 0.9455199110041632,
|
| 916 |
+
"eval_runtime": 9.3795,
|
| 917 |
+
"eval_samples_per_second": 385.523,
|
| 918 |
+
"step": 9750
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 43.81,
|
| 922 |
+
"learning_rate": 8.539823008849558e-06,
|
| 923 |
+
"loss": 0.6042,
|
| 924 |
+
"step": 9900
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 43.81,
|
| 928 |
+
"eval_loss": 0.718696653842926,
|
| 929 |
+
"eval_micro_f1": 0.9410951322431025,
|
| 930 |
+
"eval_runtime": 9.5715,
|
| 931 |
+
"eval_samples_per_second": 377.788,
|
| 932 |
+
"step": 9900
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 44.47,
|
| 936 |
+
"learning_rate": 8.517699115044249e-06,
|
| 937 |
+
"loss": 0.6018,
|
| 938 |
+
"step": 10050
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 44.47,
|
| 942 |
+
"eval_loss": 0.7181583046913147,
|
| 943 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 944 |
+
"eval_runtime": 9.5656,
|
| 945 |
+
"eval_samples_per_second": 378.02,
|
| 946 |
+
"step": 10050
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 45.13,
|
| 950 |
+
"learning_rate": 8.495575221238938e-06,
|
| 951 |
+
"loss": 0.6055,
|
| 952 |
+
"step": 10200
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 45.13,
|
| 956 |
+
"eval_loss": 0.7177845239639282,
|
| 957 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 958 |
+
"eval_runtime": 8.8211,
|
| 959 |
+
"eval_samples_per_second": 409.925,
|
| 960 |
+
"step": 10200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 45.8,
|
| 964 |
+
"learning_rate": 8.473451327433629e-06,
|
| 965 |
+
"loss": 0.6009,
|
| 966 |
+
"step": 10350
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 45.8,
|
| 970 |
+
"eval_loss": 0.7190163135528564,
|
| 971 |
+
"eval_micro_f1": 0.9433075216236328,
|
| 972 |
+
"eval_runtime": 9.5296,
|
| 973 |
+
"eval_samples_per_second": 379.451,
|
| 974 |
+
"step": 10350
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 46.46,
|
| 978 |
+
"learning_rate": 8.45132743362832e-06,
|
| 979 |
+
"loss": 0.6053,
|
| 980 |
+
"step": 10500
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 46.46,
|
| 984 |
+
"eval_loss": 0.7190549969673157,
|
| 985 |
+
"eval_micro_f1": 0.9427544242785004,
|
| 986 |
+
"eval_runtime": 9.292,
|
| 987 |
+
"eval_samples_per_second": 389.152,
|
| 988 |
+
"step": 10500
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 47.12,
|
| 992 |
+
"learning_rate": 8.42920353982301e-06,
|
| 993 |
+
"loss": 0.5996,
|
| 994 |
+
"step": 10650
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 47.12,
|
| 998 |
+
"eval_loss": 0.7188761830329895,
|
| 999 |
+
"eval_micro_f1": 0.9380530968448733,
|
| 1000 |
+
"eval_runtime": 9.6402,
|
| 1001 |
+
"eval_samples_per_second": 375.096,
|
| 1002 |
+
"step": 10650
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 47.79,
|
| 1006 |
+
"learning_rate": 8.4070796460177e-06,
|
| 1007 |
+
"loss": 0.6022,
|
| 1008 |
+
"step": 10800
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 47.79,
|
| 1012 |
+
"eval_loss": 0.7177832722663879,
|
| 1013 |
+
"eval_micro_f1": 0.9446902649864644,
|
| 1014 |
+
"eval_runtime": 9.6418,
|
| 1015 |
+
"eval_samples_per_second": 375.035,
|
| 1016 |
+
"step": 10800
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 48.45,
|
| 1020 |
+
"learning_rate": 8.38495575221239e-06,
|
| 1021 |
+
"loss": 0.6039,
|
| 1022 |
+
"step": 10950
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 48.45,
|
| 1026 |
+
"eval_loss": 0.7174757719039917,
|
| 1027 |
+
"eval_micro_f1": 0.9460730083492959,
|
| 1028 |
+
"eval_runtime": 8.7509,
|
| 1029 |
+
"eval_samples_per_second": 413.213,
|
| 1030 |
+
"step": 10950
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 49.12,
|
| 1034 |
+
"learning_rate": 8.36283185840708e-06,
|
| 1035 |
+
"loss": 0.5968,
|
| 1036 |
+
"step": 11100
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 49.12,
|
| 1040 |
+
"eval_loss": 0.7184685468673706,
|
| 1041 |
+
"eval_micro_f1": 0.9410951322431025,
|
| 1042 |
+
"eval_runtime": 9.6464,
|
| 1043 |
+
"eval_samples_per_second": 374.856,
|
| 1044 |
+
"step": 11100
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 49.78,
|
| 1048 |
+
"learning_rate": 8.340707964601771e-06,
|
| 1049 |
+
"loss": 0.5976,
|
| 1050 |
+
"step": 11250
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 49.78,
|
| 1054 |
+
"eval_loss": 0.717673659324646,
|
| 1055 |
+
"eval_micro_f1": 0.9433075216236328,
|
| 1056 |
+
"eval_runtime": 8.9187,
|
| 1057 |
+
"eval_samples_per_second": 405.439,
|
| 1058 |
+
"step": 11250
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 50.44,
|
| 1062 |
+
"learning_rate": 8.31858407079646e-06,
|
| 1063 |
+
"loss": 0.6025,
|
| 1064 |
+
"step": 11400
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 50.44,
|
| 1068 |
+
"eval_loss": 0.7185506224632263,
|
| 1069 |
+
"eval_micro_f1": 0.9482853977298262,
|
| 1070 |
+
"eval_runtime": 9.5683,
|
| 1071 |
+
"eval_samples_per_second": 377.914,
|
| 1072 |
+
"step": 11400
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 51.11,
|
| 1076 |
+
"learning_rate": 8.296460176991151e-06,
|
| 1077 |
+
"loss": 0.6045,
|
| 1078 |
+
"step": 11550
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 51.11,
|
| 1082 |
+
"eval_loss": 0.7161318063735962,
|
| 1083 |
+
"eval_micro_f1": 0.9482853977298262,
|
| 1084 |
+
"eval_runtime": 9.4873,
|
| 1085 |
+
"eval_samples_per_second": 381.139,
|
| 1086 |
+
"step": 11550
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 51.77,
|
| 1090 |
+
"learning_rate": 8.274336283185842e-06,
|
| 1091 |
+
"loss": 0.6066,
|
| 1092 |
+
"step": 11700
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 51.77,
|
| 1096 |
+
"eval_loss": 0.7150410413742065,
|
| 1097 |
+
"eval_micro_f1": 0.9504977871103566,
|
| 1098 |
+
"eval_runtime": 9.772,
|
| 1099 |
+
"eval_samples_per_second": 370.036,
|
| 1100 |
+
"step": 11700
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 52.43,
|
| 1104 |
+
"learning_rate": 8.252212389380532e-06,
|
| 1105 |
+
"loss": 0.5995,
|
| 1106 |
+
"step": 11850
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 52.43,
|
| 1110 |
+
"eval_loss": 0.7161645293235779,
|
| 1111 |
+
"eval_micro_f1": 0.952710176490887,
|
| 1112 |
+
"eval_runtime": 9.5008,
|
| 1113 |
+
"eval_samples_per_second": 380.601,
|
| 1114 |
+
"step": 11850
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 53.1,
|
| 1118 |
+
"learning_rate": 8.230088495575221e-06,
|
| 1119 |
+
"loss": 0.6021,
|
| 1120 |
+
"step": 12000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 53.1,
|
| 1124 |
+
"eval_loss": 0.7195029258728027,
|
| 1125 |
+
"eval_micro_f1": 0.9361172561369092,
|
| 1126 |
+
"eval_runtime": 10.6413,
|
| 1127 |
+
"eval_samples_per_second": 339.807,
|
| 1128 |
+
"step": 12000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 53.76,
|
| 1132 |
+
"learning_rate": 8.207964601769912e-06,
|
| 1133 |
+
"loss": 0.6027,
|
| 1134 |
+
"step": 12150
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 53.76,
|
| 1138 |
+
"eval_loss": 0.71631920337677,
|
| 1139 |
+
"eval_micro_f1": 0.954646017198851,
|
| 1140 |
+
"eval_runtime": 9.5886,
|
| 1141 |
+
"eval_samples_per_second": 377.113,
|
| 1142 |
+
"step": 12150
|
| 1143 |
+
}
|
| 1144 |
+
],
|
| 1145 |
+
"max_steps": 67800,
|
| 1146 |
+
"num_train_epochs": 300,
|
| 1147 |
+
"total_flos": 42104269489406592,
|
| 1148 |
+
"trial_name": null,
|
| 1149 |
+
"trial_params": null
|
| 1150 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1034fb299b54295696b5b0519ceb0a6e19a85b181abd8cf8409ef0077327cc7
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|