Commit
·
ffb1109
1
Parent(s):
213b206
first model version
Browse files- config.json +40 -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 +1080 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-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 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4,
|
| 27 |
+
"LABEL_5": 5
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "bert",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"transformers_version": "4.2.2",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 30522
|
| 40 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07b4464f91712e4b32916594cd5c6e9b246a29e88441512ded7eba6b39822907
|
| 3 |
+
size 876020945
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:174b2585670d4c5086482cbbc9247a8be33c686fb733bf1ac39cc98049476fe3
|
| 3 |
+
size 438036745
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a57015fc33b143acb9f645d0c49d40adb41bd61cb34740f283dee1a6713133
|
| 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, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1080 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8181818176808394,
|
| 3 |
+
"best_model_checkpoint": "../out/wnut/ner-bert-spanclass-dice/checkpoints/checkpoint-3040",
|
| 4 |
+
"epoch": 49.03225806451613,
|
| 5 |
+
"global_step": 3040,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.65,
|
| 12 |
+
"learning_rate": 9.978494623655915e-06,
|
| 13 |
+
"loss": 0.7609,
|
| 14 |
+
"step": 40
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.65,
|
| 18 |
+
"eval_loss": 0.7705183029174805,
|
| 19 |
+
"eval_micro_f1": 0.6220095688772463,
|
| 20 |
+
"eval_runtime": 5.0386,
|
| 21 |
+
"eval_samples_per_second": 165.918,
|
| 22 |
+
"step": 40
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.29,
|
| 26 |
+
"learning_rate": 9.95698924731183e-06,
|
| 27 |
+
"loss": 0.7133,
|
| 28 |
+
"step": 80
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.29,
|
| 32 |
+
"eval_loss": 0.7154462337493896,
|
| 33 |
+
"eval_micro_f1": 0.6244019133748512,
|
| 34 |
+
"eval_runtime": 2.5719,
|
| 35 |
+
"eval_samples_per_second": 325.049,
|
| 36 |
+
"step": 80
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.94,
|
| 40 |
+
"learning_rate": 9.935483870967742e-06,
|
| 41 |
+
"loss": 0.6324,
|
| 42 |
+
"step": 120
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.94,
|
| 46 |
+
"eval_loss": 0.657606840133667,
|
| 47 |
+
"eval_micro_f1": 0.759569377489522,
|
| 48 |
+
"eval_runtime": 2.5725,
|
| 49 |
+
"eval_samples_per_second": 324.971,
|
| 50 |
+
"step": 120
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.58,
|
| 54 |
+
"learning_rate": 9.913978494623658e-06,
|
| 55 |
+
"loss": 0.5726,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.58,
|
| 60 |
+
"eval_loss": 0.6323938965797424,
|
| 61 |
+
"eval_micro_f1": 0.7511961717479053,
|
| 62 |
+
"eval_runtime": 2.5886,
|
| 63 |
+
"eval_samples_per_second": 322.959,
|
| 64 |
+
"step": 160
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.23,
|
| 68 |
+
"learning_rate": 9.89247311827957e-06,
|
| 69 |
+
"loss": 0.5319,
|
| 70 |
+
"step": 200
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 3.23,
|
| 74 |
+
"eval_loss": 0.6058392524719238,
|
| 75 |
+
"eval_micro_f1": 0.7822966502167676,
|
| 76 |
+
"eval_runtime": 2.5691,
|
| 77 |
+
"eval_samples_per_second": 325.4,
|
| 78 |
+
"step": 200
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.87,
|
| 82 |
+
"learning_rate": 9.870967741935485e-06,
|
| 83 |
+
"loss": 0.4986,
|
| 84 |
+
"step": 240
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.87,
|
| 88 |
+
"eval_loss": 0.5896583199501038,
|
| 89 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 90 |
+
"eval_runtime": 2.5838,
|
| 91 |
+
"eval_samples_per_second": 323.554,
|
| 92 |
+
"step": 240
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.52,
|
| 96 |
+
"learning_rate": 9.8494623655914e-06,
|
| 97 |
+
"loss": 0.4643,
|
| 98 |
+
"step": 280
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.52,
|
| 102 |
+
"eval_loss": 0.5731987357139587,
|
| 103 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 104 |
+
"eval_runtime": 2.573,
|
| 105 |
+
"eval_samples_per_second": 324.914,
|
| 106 |
+
"step": 280
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 5.16,
|
| 110 |
+
"learning_rate": 9.827956989247312e-06,
|
| 111 |
+
"loss": 0.4218,
|
| 112 |
+
"step": 320
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 5.16,
|
| 116 |
+
"eval_loss": 0.5619742274284363,
|
| 117 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 118 |
+
"eval_runtime": 2.5828,
|
| 119 |
+
"eval_samples_per_second": 323.679,
|
| 120 |
+
"step": 320
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.81,
|
| 124 |
+
"learning_rate": 9.806451612903226e-06,
|
| 125 |
+
"loss": 0.3839,
|
| 126 |
+
"step": 360
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.81,
|
| 130 |
+
"eval_loss": 0.560495138168335,
|
| 131 |
+
"eval_micro_f1": 0.7739234444751508,
|
| 132 |
+
"eval_runtime": 2.5822,
|
| 133 |
+
"eval_samples_per_second": 323.761,
|
| 134 |
+
"step": 360
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.45,
|
| 138 |
+
"learning_rate": 9.78494623655914e-06,
|
| 139 |
+
"loss": 0.3533,
|
| 140 |
+
"step": 400
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.45,
|
| 144 |
+
"eval_loss": 0.5423776507377625,
|
| 145 |
+
"eval_micro_f1": 0.7799043057191627,
|
| 146 |
+
"eval_runtime": 5.1636,
|
| 147 |
+
"eval_samples_per_second": 161.902,
|
| 148 |
+
"step": 400
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.1,
|
| 152 |
+
"learning_rate": 9.763440860215055e-06,
|
| 153 |
+
"loss": 0.3185,
|
| 154 |
+
"step": 440
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 7.1,
|
| 158 |
+
"eval_loss": 0.5292896032333374,
|
| 159 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 160 |
+
"eval_runtime": 2.5902,
|
| 161 |
+
"eval_samples_per_second": 322.751,
|
| 162 |
+
"step": 440
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.74,
|
| 166 |
+
"learning_rate": 9.74193548387097e-06,
|
| 167 |
+
"loss": 0.2787,
|
| 168 |
+
"step": 480
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.74,
|
| 172 |
+
"eval_loss": 0.5203776955604553,
|
| 173 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 174 |
+
"eval_runtime": 2.5776,
|
| 175 |
+
"eval_samples_per_second": 324.338,
|
| 176 |
+
"step": 480
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.39,
|
| 180 |
+
"learning_rate": 9.720430107526882e-06,
|
| 181 |
+
"loss": 0.2826,
|
| 182 |
+
"step": 520
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.39,
|
| 186 |
+
"eval_loss": 0.5275840163230896,
|
| 187 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 188 |
+
"eval_runtime": 5.4507,
|
| 189 |
+
"eval_samples_per_second": 153.374,
|
| 190 |
+
"step": 520
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 9.03,
|
| 194 |
+
"learning_rate": 9.698924731182796e-06,
|
| 195 |
+
"loss": 0.2484,
|
| 196 |
+
"step": 560
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 9.03,
|
| 200 |
+
"eval_loss": 0.5161808133125305,
|
| 201 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 202 |
+
"eval_runtime": 2.5785,
|
| 203 |
+
"eval_samples_per_second": 324.22,
|
| 204 |
+
"step": 560
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 9.68,
|
| 208 |
+
"learning_rate": 9.67741935483871e-06,
|
| 209 |
+
"loss": 0.235,
|
| 210 |
+
"step": 600
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 9.68,
|
| 214 |
+
"eval_loss": 0.5403562784194946,
|
| 215 |
+
"eval_micro_f1": 0.7679425832311388,
|
| 216 |
+
"eval_runtime": 2.5747,
|
| 217 |
+
"eval_samples_per_second": 324.693,
|
| 218 |
+
"step": 600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 10.32,
|
| 222 |
+
"learning_rate": 9.655913978494625e-06,
|
| 223 |
+
"loss": 0.243,
|
| 224 |
+
"step": 640
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 10.32,
|
| 228 |
+
"eval_loss": 0.5164055824279785,
|
| 229 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 230 |
+
"eval_runtime": 2.5788,
|
| 231 |
+
"eval_samples_per_second": 324.187,
|
| 232 |
+
"step": 640
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 10.97,
|
| 236 |
+
"learning_rate": 9.634408602150539e-06,
|
| 237 |
+
"loss": 0.2209,
|
| 238 |
+
"step": 680
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 10.97,
|
| 242 |
+
"eval_loss": 0.5173386931419373,
|
| 243 |
+
"eval_micro_f1": 0.759569377489522,
|
| 244 |
+
"eval_runtime": 2.5761,
|
| 245 |
+
"eval_samples_per_second": 324.527,
|
| 246 |
+
"step": 680
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 11.61,
|
| 250 |
+
"learning_rate": 9.612903225806453e-06,
|
| 251 |
+
"loss": 0.2149,
|
| 252 |
+
"step": 720
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 11.61,
|
| 256 |
+
"eval_loss": 0.5052957534790039,
|
| 257 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 258 |
+
"eval_runtime": 2.6571,
|
| 259 |
+
"eval_samples_per_second": 314.625,
|
| 260 |
+
"step": 720
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 12.26,
|
| 264 |
+
"learning_rate": 9.591397849462366e-06,
|
| 265 |
+
"loss": 0.2225,
|
| 266 |
+
"step": 760
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 12.26,
|
| 270 |
+
"eval_loss": 0.5145884156227112,
|
| 271 |
+
"eval_micro_f1": 0.7846889947143724,
|
| 272 |
+
"eval_runtime": 2.5782,
|
| 273 |
+
"eval_samples_per_second": 324.252,
|
| 274 |
+
"step": 760
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 12.9,
|
| 278 |
+
"learning_rate": 9.56989247311828e-06,
|
| 279 |
+
"loss": 0.1907,
|
| 280 |
+
"step": 800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 12.9,
|
| 284 |
+
"eval_loss": 0.5195938348770142,
|
| 285 |
+
"eval_micro_f1": 0.7691387554799413,
|
| 286 |
+
"eval_runtime": 2.5773,
|
| 287 |
+
"eval_samples_per_second": 324.375,
|
| 288 |
+
"step": 800
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 13.55,
|
| 292 |
+
"learning_rate": 9.548387096774195e-06,
|
| 293 |
+
"loss": 0.1792,
|
| 294 |
+
"step": 840
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 13.55,
|
| 298 |
+
"eval_loss": 0.5062447190284729,
|
| 299 |
+
"eval_micro_f1": 0.777511961221558,
|
| 300 |
+
"eval_runtime": 2.572,
|
| 301 |
+
"eval_samples_per_second": 325.035,
|
| 302 |
+
"step": 840
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 14.19,
|
| 306 |
+
"learning_rate": 9.526881720430107e-06,
|
| 307 |
+
"loss": 0.1996,
|
| 308 |
+
"step": 880
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 14.19,
|
| 312 |
+
"eval_loss": 0.50869220495224,
|
| 313 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 314 |
+
"eval_runtime": 2.6593,
|
| 315 |
+
"eval_samples_per_second": 314.373,
|
| 316 |
+
"step": 880
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 14.84,
|
| 320 |
+
"learning_rate": 9.505376344086023e-06,
|
| 321 |
+
"loss": 0.218,
|
| 322 |
+
"step": 920
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 14.84,
|
| 326 |
+
"eval_loss": 0.5089221596717834,
|
| 327 |
+
"eval_micro_f1": 0.7787081334703604,
|
| 328 |
+
"eval_runtime": 4.5287,
|
| 329 |
+
"eval_samples_per_second": 184.599,
|
| 330 |
+
"step": 920
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 15.48,
|
| 334 |
+
"learning_rate": 9.483870967741936e-06,
|
| 335 |
+
"loss": 0.2129,
|
| 336 |
+
"step": 960
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 15.48,
|
| 340 |
+
"eval_loss": 0.49846795201301575,
|
| 341 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 342 |
+
"eval_runtime": 2.5705,
|
| 343 |
+
"eval_samples_per_second": 325.232,
|
| 344 |
+
"step": 960
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 16.13,
|
| 348 |
+
"learning_rate": 9.46236559139785e-06,
|
| 349 |
+
"loss": 0.1791,
|
| 350 |
+
"step": 1000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 16.13,
|
| 354 |
+
"eval_loss": 0.5086433291435242,
|
| 355 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 356 |
+
"eval_runtime": 7.0132,
|
| 357 |
+
"eval_samples_per_second": 119.204,
|
| 358 |
+
"step": 1000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 16.77,
|
| 362 |
+
"learning_rate": 9.440860215053764e-06,
|
| 363 |
+
"loss": 0.1915,
|
| 364 |
+
"step": 1040
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 16.77,
|
| 368 |
+
"eval_loss": 0.49868449568748474,
|
| 369 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 370 |
+
"eval_runtime": 2.5701,
|
| 371 |
+
"eval_samples_per_second": 325.281,
|
| 372 |
+
"step": 1040
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 17.42,
|
| 376 |
+
"learning_rate": 9.419354838709677e-06,
|
| 377 |
+
"loss": 0.1941,
|
| 378 |
+
"step": 1080
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 17.42,
|
| 382 |
+
"eval_loss": 0.4898798167705536,
|
| 383 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 384 |
+
"eval_runtime": 4.5389,
|
| 385 |
+
"eval_samples_per_second": 184.184,
|
| 386 |
+
"step": 1080
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 18.06,
|
| 390 |
+
"learning_rate": 9.397849462365593e-06,
|
| 391 |
+
"loss": 0.1925,
|
| 392 |
+
"step": 1120
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 18.06,
|
| 396 |
+
"eval_loss": 0.5056890249252319,
|
| 397 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 398 |
+
"eval_runtime": 2.5841,
|
| 399 |
+
"eval_samples_per_second": 323.522,
|
| 400 |
+
"step": 1120
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 18.71,
|
| 404 |
+
"learning_rate": 9.376344086021506e-06,
|
| 405 |
+
"loss": 0.1748,
|
| 406 |
+
"step": 1160
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 18.71,
|
| 410 |
+
"eval_loss": 0.4988904297351837,
|
| 411 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 412 |
+
"eval_runtime": 4.544,
|
| 413 |
+
"eval_samples_per_second": 183.978,
|
| 414 |
+
"step": 1160
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 19.35,
|
| 418 |
+
"learning_rate": 9.35483870967742e-06,
|
| 419 |
+
"loss": 0.182,
|
| 420 |
+
"step": 1200
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 19.35,
|
| 424 |
+
"eval_loss": 0.5048949122428894,
|
| 425 |
+
"eval_micro_f1": 0.7763157889727555,
|
| 426 |
+
"eval_runtime": 2.5956,
|
| 427 |
+
"eval_samples_per_second": 322.082,
|
| 428 |
+
"step": 1200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 20.0,
|
| 432 |
+
"learning_rate": 9.333333333333334e-06,
|
| 433 |
+
"loss": 0.1974,
|
| 434 |
+
"step": 1240
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 20.0,
|
| 438 |
+
"eval_loss": 0.5167320370674133,
|
| 439 |
+
"eval_micro_f1": 0.761961721987127,
|
| 440 |
+
"eval_runtime": 3.8728,
|
| 441 |
+
"eval_samples_per_second": 215.864,
|
| 442 |
+
"step": 1240
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 20.65,
|
| 446 |
+
"learning_rate": 9.311827956989249e-06,
|
| 447 |
+
"loss": 0.2053,
|
| 448 |
+
"step": 1280
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 20.65,
|
| 452 |
+
"eval_loss": 0.5148649215698242,
|
| 453 |
+
"eval_micro_f1": 0.7727272722263484,
|
| 454 |
+
"eval_runtime": 4.523,
|
| 455 |
+
"eval_samples_per_second": 184.832,
|
| 456 |
+
"step": 1280
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 21.29,
|
| 460 |
+
"learning_rate": 9.290322580645163e-06,
|
| 461 |
+
"loss": 0.1591,
|
| 462 |
+
"step": 1320
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 21.29,
|
| 466 |
+
"eval_loss": 0.5132973194122314,
|
| 467 |
+
"eval_micro_f1": 0.7799043057191627,
|
| 468 |
+
"eval_runtime": 2.5783,
|
| 469 |
+
"eval_samples_per_second": 324.249,
|
| 470 |
+
"step": 1320
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 21.94,
|
| 474 |
+
"learning_rate": 9.268817204301076e-06,
|
| 475 |
+
"loss": 0.1852,
|
| 476 |
+
"step": 1360
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 21.94,
|
| 480 |
+
"eval_loss": 0.49313730001449585,
|
| 481 |
+
"eval_micro_f1": 0.805023922944013,
|
| 482 |
+
"eval_runtime": 4.4012,
|
| 483 |
+
"eval_samples_per_second": 189.95,
|
| 484 |
+
"step": 1360
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 22.58,
|
| 488 |
+
"learning_rate": 9.24731182795699e-06,
|
| 489 |
+
"loss": 0.1705,
|
| 490 |
+
"step": 1400
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 22.58,
|
| 494 |
+
"eval_loss": 0.5020002722740173,
|
| 495 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 496 |
+
"eval_runtime": 4.3771,
|
| 497 |
+
"eval_samples_per_second": 190.994,
|
| 498 |
+
"step": 1400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 23.23,
|
| 502 |
+
"learning_rate": 9.225806451612904e-06,
|
| 503 |
+
"loss": 0.1774,
|
| 504 |
+
"step": 1440
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 23.23,
|
| 508 |
+
"eval_loss": 0.5008808970451355,
|
| 509 |
+
"eval_micro_f1": 0.805023922944013,
|
| 510 |
+
"eval_runtime": 6.6994,
|
| 511 |
+
"eval_samples_per_second": 124.788,
|
| 512 |
+
"step": 1440
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 23.87,
|
| 516 |
+
"learning_rate": 9.204301075268819e-06,
|
| 517 |
+
"loss": 0.1843,
|
| 518 |
+
"step": 1480
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 23.87,
|
| 522 |
+
"eval_loss": 0.4905719757080078,
|
| 523 |
+
"eval_micro_f1": 0.805023922944013,
|
| 524 |
+
"eval_runtime": 4.5018,
|
| 525 |
+
"eval_samples_per_second": 185.705,
|
| 526 |
+
"step": 1480
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 24.52,
|
| 530 |
+
"learning_rate": 9.182795698924733e-06,
|
| 531 |
+
"loss": 0.1739,
|
| 532 |
+
"step": 1520
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 24.52,
|
| 536 |
+
"eval_loss": 0.49693962931632996,
|
| 537 |
+
"eval_micro_f1": 0.78349282246557,
|
| 538 |
+
"eval_runtime": 2.8168,
|
| 539 |
+
"eval_samples_per_second": 296.786,
|
| 540 |
+
"step": 1520
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 25.16,
|
| 544 |
+
"learning_rate": 9.161290322580645e-06,
|
| 545 |
+
"loss": 0.1972,
|
| 546 |
+
"step": 1560
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 25.16,
|
| 550 |
+
"eval_loss": 0.5002193450927734,
|
| 551 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 552 |
+
"eval_runtime": 4.442,
|
| 553 |
+
"eval_samples_per_second": 188.205,
|
| 554 |
+
"step": 1560
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 25.81,
|
| 558 |
+
"learning_rate": 9.13978494623656e-06,
|
| 559 |
+
"loss": 0.1789,
|
| 560 |
+
"step": 1600
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 25.81,
|
| 564 |
+
"eval_loss": 0.49293604493141174,
|
| 565 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 566 |
+
"eval_runtime": 2.5791,
|
| 567 |
+
"eval_samples_per_second": 324.147,
|
| 568 |
+
"step": 1600
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 26.45,
|
| 572 |
+
"learning_rate": 9.118279569892474e-06,
|
| 573 |
+
"loss": 0.1647,
|
| 574 |
+
"step": 1640
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 26.45,
|
| 578 |
+
"eval_loss": 0.5105385184288025,
|
| 579 |
+
"eval_micro_f1": 0.7787081334703604,
|
| 580 |
+
"eval_runtime": 4.3949,
|
| 581 |
+
"eval_samples_per_second": 190.221,
|
| 582 |
+
"step": 1640
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 27.1,
|
| 586 |
+
"learning_rate": 9.096774193548388e-06,
|
| 587 |
+
"loss": 0.1606,
|
| 588 |
+
"step": 1680
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 27.1,
|
| 592 |
+
"eval_loss": 0.5043686032295227,
|
| 593 |
+
"eval_micro_f1": 0.7822966502167676,
|
| 594 |
+
"eval_runtime": 2.574,
|
| 595 |
+
"eval_samples_per_second": 324.785,
|
| 596 |
+
"step": 1680
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 27.74,
|
| 600 |
+
"learning_rate": 9.075268817204301e-06,
|
| 601 |
+
"loss": 0.1828,
|
| 602 |
+
"step": 1720
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 27.74,
|
| 606 |
+
"eval_loss": 0.49614059925079346,
|
| 607 |
+
"eval_micro_f1": 0.7799043057191627,
|
| 608 |
+
"eval_runtime": 3.1362,
|
| 609 |
+
"eval_samples_per_second": 266.568,
|
| 610 |
+
"step": 1720
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 28.39,
|
| 614 |
+
"learning_rate": 9.053763440860215e-06,
|
| 615 |
+
"loss": 0.1655,
|
| 616 |
+
"step": 1760
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 28.39,
|
| 620 |
+
"eval_loss": 0.49682486057281494,
|
| 621 |
+
"eval_micro_f1": 0.7846889947143724,
|
| 622 |
+
"eval_runtime": 4.4243,
|
| 623 |
+
"eval_samples_per_second": 188.957,
|
| 624 |
+
"step": 1760
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 29.03,
|
| 628 |
+
"learning_rate": 9.03225806451613e-06,
|
| 629 |
+
"loss": 0.1826,
|
| 630 |
+
"step": 1800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 29.03,
|
| 634 |
+
"eval_loss": 0.494783490896225,
|
| 635 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 636 |
+
"eval_runtime": 2.5934,
|
| 637 |
+
"eval_samples_per_second": 322.356,
|
| 638 |
+
"step": 1800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 29.68,
|
| 642 |
+
"learning_rate": 9.010752688172044e-06,
|
| 643 |
+
"loss": 0.1573,
|
| 644 |
+
"step": 1840
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 29.68,
|
| 648 |
+
"eval_loss": 0.49120277166366577,
|
| 649 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 650 |
+
"eval_runtime": 4.5606,
|
| 651 |
+
"eval_samples_per_second": 183.308,
|
| 652 |
+
"step": 1840
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 30.32,
|
| 656 |
+
"learning_rate": 8.989247311827958e-06,
|
| 657 |
+
"loss": 0.1531,
|
| 658 |
+
"step": 1880
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 30.32,
|
| 662 |
+
"eval_loss": 0.49332737922668457,
|
| 663 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 664 |
+
"eval_runtime": 2.5787,
|
| 665 |
+
"eval_samples_per_second": 324.199,
|
| 666 |
+
"step": 1880
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 30.97,
|
| 670 |
+
"learning_rate": 8.967741935483871e-06,
|
| 671 |
+
"loss": 0.1648,
|
| 672 |
+
"step": 1920
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 30.97,
|
| 676 |
+
"eval_loss": 0.49322041869163513,
|
| 677 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 678 |
+
"eval_runtime": 6.8429,
|
| 679 |
+
"eval_samples_per_second": 122.171,
|
| 680 |
+
"step": 1920
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 31.61,
|
| 684 |
+
"learning_rate": 8.946236559139785e-06,
|
| 685 |
+
"loss": 0.1524,
|
| 686 |
+
"step": 1960
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 31.61,
|
| 690 |
+
"eval_loss": 0.49640557169914246,
|
| 691 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 692 |
+
"eval_runtime": 4.4123,
|
| 693 |
+
"eval_samples_per_second": 189.472,
|
| 694 |
+
"step": 1960
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 32.26,
|
| 698 |
+
"learning_rate": 8.9247311827957e-06,
|
| 699 |
+
"loss": 0.18,
|
| 700 |
+
"step": 2000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 32.26,
|
| 704 |
+
"eval_loss": 0.48521941900253296,
|
| 705 |
+
"eval_micro_f1": 0.801435406197606,
|
| 706 |
+
"eval_runtime": 6.7049,
|
| 707 |
+
"eval_samples_per_second": 124.686,
|
| 708 |
+
"step": 2000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 32.9,
|
| 712 |
+
"learning_rate": 8.903225806451614e-06,
|
| 713 |
+
"loss": 0.1374,
|
| 714 |
+
"step": 2040
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 32.9,
|
| 718 |
+
"eval_loss": 0.49140119552612305,
|
| 719 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 720 |
+
"eval_runtime": 6.3223,
|
| 721 |
+
"eval_samples_per_second": 132.23,
|
| 722 |
+
"step": 2040
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 33.55,
|
| 726 |
+
"learning_rate": 8.881720430107528e-06,
|
| 727 |
+
"loss": 0.1694,
|
| 728 |
+
"step": 2080
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 33.55,
|
| 732 |
+
"eval_loss": 0.4927099347114563,
|
| 733 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 734 |
+
"eval_runtime": 3.7769,
|
| 735 |
+
"eval_samples_per_second": 221.347,
|
| 736 |
+
"step": 2080
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 34.19,
|
| 740 |
+
"learning_rate": 8.86021505376344e-06,
|
| 741 |
+
"loss": 0.1601,
|
| 742 |
+
"step": 2120
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 34.19,
|
| 746 |
+
"eval_loss": 0.4943098723888397,
|
| 747 |
+
"eval_micro_f1": 0.78349282246557,
|
| 748 |
+
"eval_runtime": 4.9398,
|
| 749 |
+
"eval_samples_per_second": 169.237,
|
| 750 |
+
"step": 2120
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 34.84,
|
| 754 |
+
"learning_rate": 8.838709677419357e-06,
|
| 755 |
+
"loss": 0.1319,
|
| 756 |
+
"step": 2160
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 34.84,
|
| 760 |
+
"eval_loss": 0.4894709587097168,
|
| 761 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 762 |
+
"eval_runtime": 5.4431,
|
| 763 |
+
"eval_samples_per_second": 153.588,
|
| 764 |
+
"step": 2160
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 35.48,
|
| 768 |
+
"learning_rate": 8.81720430107527e-06,
|
| 769 |
+
"loss": 0.1273,
|
| 770 |
+
"step": 2200
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 35.48,
|
| 774 |
+
"eval_loss": 0.4995502531528473,
|
| 775 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 776 |
+
"eval_runtime": 4.4194,
|
| 777 |
+
"eval_samples_per_second": 189.168,
|
| 778 |
+
"step": 2200
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 36.13,
|
| 782 |
+
"learning_rate": 8.795698924731184e-06,
|
| 783 |
+
"loss": 0.1674,
|
| 784 |
+
"step": 2240
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 36.13,
|
| 788 |
+
"eval_loss": 0.49648988246917725,
|
| 789 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 790 |
+
"eval_runtime": 5.2767,
|
| 791 |
+
"eval_samples_per_second": 158.432,
|
| 792 |
+
"step": 2240
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 36.77,
|
| 796 |
+
"learning_rate": 8.774193548387098e-06,
|
| 797 |
+
"loss": 0.1789,
|
| 798 |
+
"step": 2280
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 36.77,
|
| 802 |
+
"eval_loss": 0.5074620842933655,
|
| 803 |
+
"eval_micro_f1": 0.7523923439967076,
|
| 804 |
+
"eval_runtime": 2.5902,
|
| 805 |
+
"eval_samples_per_second": 322.751,
|
| 806 |
+
"step": 2280
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 37.42,
|
| 810 |
+
"learning_rate": 8.75268817204301e-06,
|
| 811 |
+
"loss": 0.1752,
|
| 812 |
+
"step": 2320
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 37.42,
|
| 816 |
+
"eval_loss": 0.49217045307159424,
|
| 817 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 818 |
+
"eval_runtime": 4.548,
|
| 819 |
+
"eval_samples_per_second": 183.818,
|
| 820 |
+
"step": 2320
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 38.06,
|
| 824 |
+
"learning_rate": 8.731182795698927e-06,
|
| 825 |
+
"loss": 0.1476,
|
| 826 |
+
"step": 2360
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 38.06,
|
| 830 |
+
"eval_loss": 0.49000826478004456,
|
| 831 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 832 |
+
"eval_runtime": 6.9763,
|
| 833 |
+
"eval_samples_per_second": 119.835,
|
| 834 |
+
"step": 2360
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 38.71,
|
| 838 |
+
"learning_rate": 8.70967741935484e-06,
|
| 839 |
+
"loss": 0.1868,
|
| 840 |
+
"step": 2400
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 38.71,
|
| 844 |
+
"eval_loss": 0.49217844009399414,
|
| 845 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 846 |
+
"eval_runtime": 3.4731,
|
| 847 |
+
"eval_samples_per_second": 240.707,
|
| 848 |
+
"step": 2400
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 39.35,
|
| 852 |
+
"learning_rate": 8.688172043010754e-06,
|
| 853 |
+
"loss": 0.1714,
|
| 854 |
+
"step": 2440
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 39.35,
|
| 858 |
+
"eval_loss": 0.49292442202568054,
|
| 859 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 860 |
+
"eval_runtime": 4.4418,
|
| 861 |
+
"eval_samples_per_second": 188.211,
|
| 862 |
+
"step": 2440
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 40.0,
|
| 866 |
+
"learning_rate": 8.666666666666668e-06,
|
| 867 |
+
"loss": 0.1466,
|
| 868 |
+
"step": 2480
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 40.0,
|
| 872 |
+
"eval_loss": 0.4939003586769104,
|
| 873 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 874 |
+
"eval_runtime": 7.0534,
|
| 875 |
+
"eval_samples_per_second": 118.524,
|
| 876 |
+
"step": 2480
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 40.65,
|
| 880 |
+
"learning_rate": 8.64516129032258e-06,
|
| 881 |
+
"loss": 0.1461,
|
| 882 |
+
"step": 2520
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 40.65,
|
| 886 |
+
"eval_loss": 0.5058996677398682,
|
| 887 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 888 |
+
"eval_runtime": 5.5612,
|
| 889 |
+
"eval_samples_per_second": 150.327,
|
| 890 |
+
"step": 2520
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 41.29,
|
| 894 |
+
"learning_rate": 8.623655913978495e-06,
|
| 895 |
+
"loss": 0.1778,
|
| 896 |
+
"step": 2560
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 41.29,
|
| 900 |
+
"eval_loss": 0.486485093832016,
|
| 901 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 902 |
+
"eval_runtime": 4.3478,
|
| 903 |
+
"eval_samples_per_second": 192.28,
|
| 904 |
+
"step": 2560
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 41.94,
|
| 908 |
+
"learning_rate": 8.602150537634409e-06,
|
| 909 |
+
"loss": 0.1675,
|
| 910 |
+
"step": 2600
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 41.94,
|
| 914 |
+
"eval_loss": 0.5116675496101379,
|
| 915 |
+
"eval_micro_f1": 0.7739234444751508,
|
| 916 |
+
"eval_runtime": 2.6063,
|
| 917 |
+
"eval_samples_per_second": 320.761,
|
| 918 |
+
"step": 2600
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 42.58,
|
| 922 |
+
"learning_rate": 8.580645161290323e-06,
|
| 923 |
+
"loss": 0.1468,
|
| 924 |
+
"step": 2640
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 42.58,
|
| 928 |
+
"eval_loss": 0.49054816365242004,
|
| 929 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 930 |
+
"eval_runtime": 4.4425,
|
| 931 |
+
"eval_samples_per_second": 188.184,
|
| 932 |
+
"step": 2640
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 43.23,
|
| 936 |
+
"learning_rate": 8.559139784946238e-06,
|
| 937 |
+
"loss": 0.1738,
|
| 938 |
+
"step": 2680
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 43.23,
|
| 942 |
+
"eval_loss": 0.4893950819969177,
|
| 943 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 944 |
+
"eval_runtime": 4.4169,
|
| 945 |
+
"eval_samples_per_second": 189.272,
|
| 946 |
+
"step": 2680
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 43.87,
|
| 950 |
+
"learning_rate": 8.537634408602152e-06,
|
| 951 |
+
"loss": 0.1579,
|
| 952 |
+
"step": 2720
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 43.87,
|
| 956 |
+
"eval_loss": 0.4949648082256317,
|
| 957 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 958 |
+
"eval_runtime": 5.9011,
|
| 959 |
+
"eval_samples_per_second": 141.669,
|
| 960 |
+
"step": 2720
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 44.52,
|
| 964 |
+
"learning_rate": 8.516129032258065e-06,
|
| 965 |
+
"loss": 0.1556,
|
| 966 |
+
"step": 2760
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 44.52,
|
| 970 |
+
"eval_loss": 0.48870715498924255,
|
| 971 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 972 |
+
"eval_runtime": 7.1164,
|
| 973 |
+
"eval_samples_per_second": 117.475,
|
| 974 |
+
"step": 2760
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 45.16,
|
| 978 |
+
"learning_rate": 8.494623655913979e-06,
|
| 979 |
+
"loss": 0.169,
|
| 980 |
+
"step": 2800
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 45.16,
|
| 984 |
+
"eval_loss": 0.4876663088798523,
|
| 985 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 986 |
+
"eval_runtime": 2.5733,
|
| 987 |
+
"eval_samples_per_second": 324.876,
|
| 988 |
+
"step": 2800
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 45.81,
|
| 992 |
+
"learning_rate": 8.473118279569893e-06,
|
| 993 |
+
"loss": 0.1659,
|
| 994 |
+
"step": 2840
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 45.81,
|
| 998 |
+
"eval_loss": 0.48851579427719116,
|
| 999 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 1000 |
+
"eval_runtime": 7.1719,
|
| 1001 |
+
"eval_samples_per_second": 116.566,
|
| 1002 |
+
"step": 2840
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 46.45,
|
| 1006 |
+
"learning_rate": 8.451612903225808e-06,
|
| 1007 |
+
"loss": 0.1621,
|
| 1008 |
+
"step": 2880
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 46.45,
|
| 1012 |
+
"eval_loss": 0.48815056681632996,
|
| 1013 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 1014 |
+
"eval_runtime": 5.0889,
|
| 1015 |
+
"eval_samples_per_second": 164.28,
|
| 1016 |
+
"step": 2880
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 47.1,
|
| 1020 |
+
"learning_rate": 8.430107526881722e-06,
|
| 1021 |
+
"loss": 0.1667,
|
| 1022 |
+
"step": 2920
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 47.1,
|
| 1026 |
+
"eval_loss": 0.49084004759788513,
|
| 1027 |
+
"eval_micro_f1": 0.78349282246557,
|
| 1028 |
+
"eval_runtime": 2.5855,
|
| 1029 |
+
"eval_samples_per_second": 323.336,
|
| 1030 |
+
"step": 2920
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 47.74,
|
| 1034 |
+
"learning_rate": 8.408602150537634e-06,
|
| 1035 |
+
"loss": 0.1697,
|
| 1036 |
+
"step": 2960
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 47.74,
|
| 1040 |
+
"eval_loss": 0.4899657368659973,
|
| 1041 |
+
"eval_micro_f1": 0.78349282246557,
|
| 1042 |
+
"eval_runtime": 7.1881,
|
| 1043 |
+
"eval_samples_per_second": 116.303,
|
| 1044 |
+
"step": 2960
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 48.39,
|
| 1048 |
+
"learning_rate": 8.387096774193549e-06,
|
| 1049 |
+
"loss": 0.1446,
|
| 1050 |
+
"step": 3000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 48.39,
|
| 1054 |
+
"eval_loss": 0.47679710388183594,
|
| 1055 |
+
"eval_micro_f1": 0.801435406197606,
|
| 1056 |
+
"eval_runtime": 2.5746,
|
| 1057 |
+
"eval_samples_per_second": 324.715,
|
| 1058 |
+
"step": 3000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 49.03,
|
| 1062 |
+
"learning_rate": 8.365591397849463e-06,
|
| 1063 |
+
"loss": 0.1364,
|
| 1064 |
+
"step": 3040
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 49.03,
|
| 1068 |
+
"eval_loss": 0.4702768921852112,
|
| 1069 |
+
"eval_micro_f1": 0.8181818176808394,
|
| 1070 |
+
"eval_runtime": 4.5292,
|
| 1071 |
+
"eval_samples_per_second": 184.582,
|
| 1072 |
+
"step": 3040
|
| 1073 |
+
}
|
| 1074 |
+
],
|
| 1075 |
+
"max_steps": 18600,
|
| 1076 |
+
"num_train_epochs": 300,
|
| 1077 |
+
"total_flos": 4154829689883924,
|
| 1078 |
+
"trial_name": null,
|
| 1079 |
+
"trial_params": null
|
| 1080 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a13884b1a332024118b685658d5d797ccd7833dcb17ecd0378054bde1c95ff0f
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|