Commit ·
d5cbbc6
1
Parent(s): 6a111a5
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 +2452 -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:af15c9fab49a9c602218bdc17305d3737754c4342cfdc4fd826c20bd7d461361
|
| 3 |
+
size 876020945
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b845fabdfff9eee57755d4821803dbf5602e16267f7c6257cb876893bb61bd7
|
| 3 |
+
size 438036745
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4932a9947740ed4d343457356f79656c2844d6e4909f06fb3b6546430401f2a6
|
| 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 +1,2452 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8205741621784443,
|
| 3 |
+
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/class/run-42/checkpoints/checkpoint-3000",
|
| 4 |
+
"epoch": 187.5,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.62,
|
| 12 |
+
"eval_loss": 1.6759881973266602,
|
| 13 |
+
"eval_micro_f1": 0.08851674591137737,
|
| 14 |
+
"eval_runtime": 1.3359,
|
| 15 |
+
"eval_samples_per_second": 625.794,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.25,
|
| 20 |
+
"eval_loss": 1.5462044477462769,
|
| 21 |
+
"eval_micro_f1": 0.6052631573940128,
|
| 22 |
+
"eval_runtime": 1.2101,
|
| 23 |
+
"eval_samples_per_second": 690.875,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.88,
|
| 28 |
+
"eval_loss": 1.3322491645812988,
|
| 29 |
+
"eval_micro_f1": 0.6244019133748512,
|
| 30 |
+
"eval_runtime": 0.8599,
|
| 31 |
+
"eval_samples_per_second": 972.239,
|
| 32 |
+
"step": 30
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.5,
|
| 36 |
+
"eval_loss": 1.1252518892288208,
|
| 37 |
+
"eval_micro_f1": 0.644736841604492,
|
| 38 |
+
"eval_runtime": 1.1837,
|
| 39 |
+
"eval_samples_per_second": 706.251,
|
| 40 |
+
"step": 40
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.12,
|
| 44 |
+
"eval_loss": 1.0135610103607178,
|
| 45 |
+
"eval_micro_f1": 0.6387559803604799,
|
| 46 |
+
"eval_runtime": 1.2916,
|
| 47 |
+
"eval_samples_per_second": 647.281,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.75,
|
| 52 |
+
"eval_loss": 0.9341530203819275,
|
| 53 |
+
"eval_micro_f1": 0.6411483248580847,
|
| 54 |
+
"eval_runtime": 1.1548,
|
| 55 |
+
"eval_samples_per_second": 723.953,
|
| 56 |
+
"step": 60
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.38,
|
| 60 |
+
"eval_loss": 0.8877728581428528,
|
| 61 |
+
"eval_micro_f1": 0.644736841604492,
|
| 62 |
+
"eval_runtime": 1.2673,
|
| 63 |
+
"eval_samples_per_second": 659.646,
|
| 64 |
+
"step": 70
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"eval_loss": 0.8828455209732056,
|
| 69 |
+
"eval_micro_f1": 0.6459330138532943,
|
| 70 |
+
"eval_runtime": 0.8582,
|
| 71 |
+
"eval_samples_per_second": 974.142,
|
| 72 |
+
"step": 80
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.62,
|
| 76 |
+
"eval_loss": 0.887384295463562,
|
| 77 |
+
"eval_micro_f1": 0.6794258368197614,
|
| 78 |
+
"eval_runtime": 1.2161,
|
| 79 |
+
"eval_samples_per_second": 687.446,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.25,
|
| 84 |
+
"eval_loss": 0.7980366945266724,
|
| 85 |
+
"eval_micro_f1": 0.7368421047622765,
|
| 86 |
+
"eval_runtime": 1.168,
|
| 87 |
+
"eval_samples_per_second": 715.781,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.88,
|
| 92 |
+
"eval_loss": 0.7685986161231995,
|
| 93 |
+
"eval_micro_f1": 0.759569377489522,
|
| 94 |
+
"eval_runtime": 1.2908,
|
| 95 |
+
"eval_samples_per_second": 647.674,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.5,
|
| 100 |
+
"eval_loss": 0.7412388324737549,
|
| 101 |
+
"eval_micro_f1": 0.7811004779679651,
|
| 102 |
+
"eval_runtime": 0.865,
|
| 103 |
+
"eval_samples_per_second": 966.496,
|
| 104 |
+
"step": 120
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.12,
|
| 108 |
+
"eval_loss": 0.736153781414032,
|
| 109 |
+
"eval_micro_f1": 0.777511961221558,
|
| 110 |
+
"eval_runtime": 0.8746,
|
| 111 |
+
"eval_samples_per_second": 955.819,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.75,
|
| 116 |
+
"eval_loss": 0.741908848285675,
|
| 117 |
+
"eval_micro_f1": 0.7787081334703604,
|
| 118 |
+
"eval_runtime": 1.2436,
|
| 119 |
+
"eval_samples_per_second": 672.264,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.38,
|
| 124 |
+
"eval_loss": 0.7110205888748169,
|
| 125 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 126 |
+
"eval_runtime": 4.1459,
|
| 127 |
+
"eval_samples_per_second": 201.643,
|
| 128 |
+
"step": 150
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"eval_loss": 0.743588387966156,
|
| 133 |
+
"eval_micro_f1": 0.7703349277287436,
|
| 134 |
+
"eval_runtime": 1.2283,
|
| 135 |
+
"eval_samples_per_second": 680.592,
|
| 136 |
+
"step": 160
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 10.62,
|
| 140 |
+
"eval_loss": 0.6968352198600769,
|
| 141 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 142 |
+
"eval_runtime": 1.1871,
|
| 143 |
+
"eval_samples_per_second": 704.248,
|
| 144 |
+
"step": 170
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 11.25,
|
| 148 |
+
"eval_loss": 0.7096373438835144,
|
| 149 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 150 |
+
"eval_runtime": 0.8786,
|
| 151 |
+
"eval_samples_per_second": 951.476,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 11.88,
|
| 156 |
+
"eval_loss": 0.7048764228820801,
|
| 157 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 158 |
+
"eval_runtime": 1.3421,
|
| 159 |
+
"eval_samples_per_second": 622.892,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 12.5,
|
| 164 |
+
"eval_loss": 0.7515257596969604,
|
| 165 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 166 |
+
"eval_runtime": 1.2546,
|
| 167 |
+
"eval_samples_per_second": 666.338,
|
| 168 |
+
"step": 200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.12,
|
| 172 |
+
"eval_loss": 0.7905582785606384,
|
| 173 |
+
"eval_micro_f1": 0.7739234444751508,
|
| 174 |
+
"eval_runtime": 1.2206,
|
| 175 |
+
"eval_samples_per_second": 684.892,
|
| 176 |
+
"step": 210
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.75,
|
| 180 |
+
"eval_loss": 0.7019672393798828,
|
| 181 |
+
"eval_micro_f1": 0.8145933009344323,
|
| 182 |
+
"eval_runtime": 1.1469,
|
| 183 |
+
"eval_samples_per_second": 728.9,
|
| 184 |
+
"step": 220
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 14.38,
|
| 188 |
+
"eval_loss": 0.743220865726471,
|
| 189 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 190 |
+
"eval_runtime": 0.8806,
|
| 191 |
+
"eval_samples_per_second": 949.347,
|
| 192 |
+
"step": 230
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 15.0,
|
| 196 |
+
"eval_loss": 0.7914738059043884,
|
| 197 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 198 |
+
"eval_runtime": 1.246,
|
| 199 |
+
"eval_samples_per_second": 670.957,
|
| 200 |
+
"step": 240
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 15.62,
|
| 204 |
+
"eval_loss": 0.8315173983573914,
|
| 205 |
+
"eval_micro_f1": 0.7799043057191627,
|
| 206 |
+
"eval_runtime": 1.621,
|
| 207 |
+
"eval_samples_per_second": 515.725,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 16.25,
|
| 212 |
+
"eval_loss": 0.8176524043083191,
|
| 213 |
+
"eval_micro_f1": 0.7846889947143724,
|
| 214 |
+
"eval_runtime": 1.2095,
|
| 215 |
+
"eval_samples_per_second": 691.193,
|
| 216 |
+
"step": 260
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 16.88,
|
| 220 |
+
"eval_loss": 0.9075602889060974,
|
| 221 |
+
"eval_micro_f1": 0.771531099977546,
|
| 222 |
+
"eval_runtime": 1.2256,
|
| 223 |
+
"eval_samples_per_second": 682.12,
|
| 224 |
+
"step": 270
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 17.5,
|
| 228 |
+
"eval_loss": 0.8281694650650024,
|
| 229 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 230 |
+
"eval_runtime": 0.8715,
|
| 231 |
+
"eval_samples_per_second": 959.275,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 18.12,
|
| 236 |
+
"eval_loss": 0.8547766208648682,
|
| 237 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 238 |
+
"eval_runtime": 1.2407,
|
| 239 |
+
"eval_samples_per_second": 673.819,
|
| 240 |
+
"step": 290
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 18.75,
|
| 244 |
+
"eval_loss": 0.8972189426422119,
|
| 245 |
+
"eval_micro_f1": 0.7822966502167676,
|
| 246 |
+
"eval_runtime": 1.208,
|
| 247 |
+
"eval_samples_per_second": 692.055,
|
| 248 |
+
"step": 300
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 19.38,
|
| 252 |
+
"eval_loss": 0.9401060938835144,
|
| 253 |
+
"eval_micro_f1": 0.7787081334703604,
|
| 254 |
+
"eval_runtime": 1.1982,
|
| 255 |
+
"eval_samples_per_second": 697.732,
|
| 256 |
+
"step": 310
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 20.0,
|
| 260 |
+
"eval_loss": 0.9120603799819946,
|
| 261 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 262 |
+
"eval_runtime": 1.2047,
|
| 263 |
+
"eval_samples_per_second": 693.932,
|
| 264 |
+
"step": 320
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 20.62,
|
| 268 |
+
"eval_loss": 0.920120358467102,
|
| 269 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 270 |
+
"eval_runtime": 0.8725,
|
| 271 |
+
"eval_samples_per_second": 958.217,
|
| 272 |
+
"step": 330
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 21.25,
|
| 276 |
+
"eval_loss": 0.9525130987167358,
|
| 277 |
+
"eval_micro_f1": 0.771531099977546,
|
| 278 |
+
"eval_runtime": 1.1953,
|
| 279 |
+
"eval_samples_per_second": 699.415,
|
| 280 |
+
"step": 340
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 21.88,
|
| 284 |
+
"eval_loss": 0.9583889245986938,
|
| 285 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 286 |
+
"eval_runtime": 1.2359,
|
| 287 |
+
"eval_samples_per_second": 676.414,
|
| 288 |
+
"step": 350
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 22.5,
|
| 292 |
+
"eval_loss": 1.0320873260498047,
|
| 293 |
+
"eval_micro_f1": 0.7739234444751508,
|
| 294 |
+
"eval_runtime": 1.1982,
|
| 295 |
+
"eval_samples_per_second": 697.705,
|
| 296 |
+
"step": 360
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 23.12,
|
| 300 |
+
"eval_loss": 0.9924129247665405,
|
| 301 |
+
"eval_micro_f1": 0.7751196167239531,
|
| 302 |
+
"eval_runtime": 1.2948,
|
| 303 |
+
"eval_samples_per_second": 645.665,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 23.75,
|
| 308 |
+
"eval_loss": 0.919312059879303,
|
| 309 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 310 |
+
"eval_runtime": 1.2586,
|
| 311 |
+
"eval_samples_per_second": 664.256,
|
| 312 |
+
"step": 380
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 24.38,
|
| 316 |
+
"eval_loss": 1.0358171463012695,
|
| 317 |
+
"eval_micro_f1": 0.7751196167239531,
|
| 318 |
+
"eval_runtime": 1.2561,
|
| 319 |
+
"eval_samples_per_second": 665.549,
|
| 320 |
+
"step": 390
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 25.0,
|
| 324 |
+
"eval_loss": 1.0559030771255493,
|
| 325 |
+
"eval_micro_f1": 0.7787081334703604,
|
| 326 |
+
"eval_runtime": 1.2969,
|
| 327 |
+
"eval_samples_per_second": 644.633,
|
| 328 |
+
"step": 400
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 25.62,
|
| 332 |
+
"eval_loss": 0.9812420606613159,
|
| 333 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 334 |
+
"eval_runtime": 1.2399,
|
| 335 |
+
"eval_samples_per_second": 674.266,
|
| 336 |
+
"step": 410
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 26.25,
|
| 340 |
+
"eval_loss": 1.0270429849624634,
|
| 341 |
+
"eval_micro_f1": 0.7799043057191627,
|
| 342 |
+
"eval_runtime": 1.332,
|
| 343 |
+
"eval_samples_per_second": 627.648,
|
| 344 |
+
"step": 420
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 26.88,
|
| 348 |
+
"eval_loss": 1.044345736503601,
|
| 349 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 350 |
+
"eval_runtime": 1.2183,
|
| 351 |
+
"eval_samples_per_second": 686.179,
|
| 352 |
+
"step": 430
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 27.5,
|
| 356 |
+
"eval_loss": 1.0406349897384644,
|
| 357 |
+
"eval_micro_f1": 0.7846889947143724,
|
| 358 |
+
"eval_runtime": 0.8726,
|
| 359 |
+
"eval_samples_per_second": 958.035,
|
| 360 |
+
"step": 440
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 28.12,
|
| 364 |
+
"eval_loss": 0.9970749616622925,
|
| 365 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 366 |
+
"eval_runtime": 1.1767,
|
| 367 |
+
"eval_samples_per_second": 710.432,
|
| 368 |
+
"step": 450
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 28.75,
|
| 372 |
+
"eval_loss": 1.0192404985427856,
|
| 373 |
+
"eval_micro_f1": 0.801435406197606,
|
| 374 |
+
"eval_runtime": 1.1984,
|
| 375 |
+
"eval_samples_per_second": 697.599,
|
| 376 |
+
"step": 460
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 29.38,
|
| 380 |
+
"eval_loss": 1.1054484844207764,
|
| 381 |
+
"eval_micro_f1": 0.78349282246557,
|
| 382 |
+
"eval_runtime": 1.3117,
|
| 383 |
+
"eval_samples_per_second": 637.324,
|
| 384 |
+
"step": 470
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.0,
|
| 388 |
+
"eval_loss": 1.1029002666473389,
|
| 389 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 390 |
+
"eval_runtime": 1.2415,
|
| 391 |
+
"eval_samples_per_second": 673.362,
|
| 392 |
+
"step": 480
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 30.62,
|
| 396 |
+
"eval_loss": 1.041625738143921,
|
| 397 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 398 |
+
"eval_runtime": 1.0809,
|
| 399 |
+
"eval_samples_per_second": 773.41,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 31.25,
|
| 404 |
+
"learning_rate": 8.958333333333334e-06,
|
| 405 |
+
"loss": 0.3178,
|
| 406 |
+
"step": 500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 31.25,
|
| 410 |
+
"eval_loss": 1.0797942876815796,
|
| 411 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 412 |
+
"eval_runtime": 1.252,
|
| 413 |
+
"eval_samples_per_second": 667.722,
|
| 414 |
+
"step": 500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 31.88,
|
| 418 |
+
"eval_loss": 1.1399964094161987,
|
| 419 |
+
"eval_micro_f1": 0.7846889947143724,
|
| 420 |
+
"eval_runtime": 1.1939,
|
| 421 |
+
"eval_samples_per_second": 700.251,
|
| 422 |
+
"step": 510
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 32.5,
|
| 426 |
+
"eval_loss": 1.1625529527664185,
|
| 427 |
+
"eval_micro_f1": 0.7739234444751508,
|
| 428 |
+
"eval_runtime": 1.2201,
|
| 429 |
+
"eval_samples_per_second": 685.212,
|
| 430 |
+
"step": 520
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 33.12,
|
| 434 |
+
"eval_loss": 1.104368805885315,
|
| 435 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 436 |
+
"eval_runtime": 1.2001,
|
| 437 |
+
"eval_samples_per_second": 696.612,
|
| 438 |
+
"step": 530
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 33.75,
|
| 442 |
+
"eval_loss": 1.077760100364685,
|
| 443 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 444 |
+
"eval_runtime": 0.8761,
|
| 445 |
+
"eval_samples_per_second": 954.202,
|
| 446 |
+
"step": 540
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 34.38,
|
| 450 |
+
"eval_loss": 1.1734049320220947,
|
| 451 |
+
"eval_micro_f1": 0.7822966502167676,
|
| 452 |
+
"eval_runtime": 1.2138,
|
| 453 |
+
"eval_samples_per_second": 688.726,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 35.0,
|
| 458 |
+
"eval_loss": 1.1793453693389893,
|
| 459 |
+
"eval_micro_f1": 0.78349282246557,
|
| 460 |
+
"eval_runtime": 1.5359,
|
| 461 |
+
"eval_samples_per_second": 544.292,
|
| 462 |
+
"step": 560
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 35.62,
|
| 466 |
+
"eval_loss": 1.1454592943191528,
|
| 467 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 468 |
+
"eval_runtime": 1.2532,
|
| 469 |
+
"eval_samples_per_second": 667.093,
|
| 470 |
+
"step": 570
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 36.25,
|
| 474 |
+
"eval_loss": 1.1729267835617065,
|
| 475 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 476 |
+
"eval_runtime": 1.2523,
|
| 477 |
+
"eval_samples_per_second": 667.549,
|
| 478 |
+
"step": 580
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 36.88,
|
| 482 |
+
"eval_loss": 1.1719892024993896,
|
| 483 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 484 |
+
"eval_runtime": 3.7258,
|
| 485 |
+
"eval_samples_per_second": 224.381,
|
| 486 |
+
"step": 590
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 37.5,
|
| 490 |
+
"eval_loss": 1.1657602787017822,
|
| 491 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 492 |
+
"eval_runtime": 1.2367,
|
| 493 |
+
"eval_samples_per_second": 675.991,
|
| 494 |
+
"step": 600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 38.12,
|
| 498 |
+
"eval_loss": 1.1762133836746216,
|
| 499 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 500 |
+
"eval_runtime": 1.223,
|
| 501 |
+
"eval_samples_per_second": 683.542,
|
| 502 |
+
"step": 610
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 38.75,
|
| 506 |
+
"eval_loss": 1.1761835813522339,
|
| 507 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 508 |
+
"eval_runtime": 1.214,
|
| 509 |
+
"eval_samples_per_second": 688.657,
|
| 510 |
+
"step": 620
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 39.38,
|
| 514 |
+
"eval_loss": 1.1437163352966309,
|
| 515 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 516 |
+
"eval_runtime": 1.2096,
|
| 517 |
+
"eval_samples_per_second": 691.162,
|
| 518 |
+
"step": 630
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 40.0,
|
| 522 |
+
"eval_loss": 1.1287521123886108,
|
| 523 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 524 |
+
"eval_runtime": 0.8722,
|
| 525 |
+
"eval_samples_per_second": 958.491,
|
| 526 |
+
"step": 640
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 40.62,
|
| 530 |
+
"eval_loss": 1.1567052602767944,
|
| 531 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 532 |
+
"eval_runtime": 1.1829,
|
| 533 |
+
"eval_samples_per_second": 706.74,
|
| 534 |
+
"step": 650
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 41.25,
|
| 538 |
+
"eval_loss": 1.1617976427078247,
|
| 539 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 540 |
+
"eval_runtime": 1.6636,
|
| 541 |
+
"eval_samples_per_second": 502.511,
|
| 542 |
+
"step": 660
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 41.88,
|
| 546 |
+
"eval_loss": 1.1672464609146118,
|
| 547 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 548 |
+
"eval_runtime": 1.2985,
|
| 549 |
+
"eval_samples_per_second": 643.836,
|
| 550 |
+
"step": 670
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 42.5,
|
| 554 |
+
"eval_loss": 1.1712684631347656,
|
| 555 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 556 |
+
"eval_runtime": 1.1903,
|
| 557 |
+
"eval_samples_per_second": 702.367,
|
| 558 |
+
"step": 680
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 43.12,
|
| 562 |
+
"eval_loss": 1.1998251676559448,
|
| 563 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 564 |
+
"eval_runtime": 0.8749,
|
| 565 |
+
"eval_samples_per_second": 955.576,
|
| 566 |
+
"step": 690
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 43.75,
|
| 570 |
+
"eval_loss": 1.1978861093521118,
|
| 571 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 572 |
+
"eval_runtime": 1.209,
|
| 573 |
+
"eval_samples_per_second": 691.482,
|
| 574 |
+
"step": 700
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 44.38,
|
| 578 |
+
"eval_loss": 1.2747777700424194,
|
| 579 |
+
"eval_micro_f1": 0.777511961221558,
|
| 580 |
+
"eval_runtime": 1.2446,
|
| 581 |
+
"eval_samples_per_second": 671.714,
|
| 582 |
+
"step": 710
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 45.0,
|
| 586 |
+
"eval_loss": 1.265109896659851,
|
| 587 |
+
"eval_micro_f1": 0.7727272722263484,
|
| 588 |
+
"eval_runtime": 1.3112,
|
| 589 |
+
"eval_samples_per_second": 637.588,
|
| 590 |
+
"step": 720
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 45.62,
|
| 594 |
+
"eval_loss": 1.2195650339126587,
|
| 595 |
+
"eval_micro_f1": 0.78349282246557,
|
| 596 |
+
"eval_runtime": 1.2682,
|
| 597 |
+
"eval_samples_per_second": 659.204,
|
| 598 |
+
"step": 730
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 46.25,
|
| 602 |
+
"eval_loss": 1.2457984685897827,
|
| 603 |
+
"eval_micro_f1": 0.7822966502167676,
|
| 604 |
+
"eval_runtime": 0.8903,
|
| 605 |
+
"eval_samples_per_second": 939.024,
|
| 606 |
+
"step": 740
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 46.88,
|
| 610 |
+
"eval_loss": 1.1744990348815918,
|
| 611 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 612 |
+
"eval_runtime": 1.3358,
|
| 613 |
+
"eval_samples_per_second": 625.839,
|
| 614 |
+
"step": 750
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 47.5,
|
| 618 |
+
"eval_loss": 1.203239917755127,
|
| 619 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 620 |
+
"eval_runtime": 1.6763,
|
| 621 |
+
"eval_samples_per_second": 498.716,
|
| 622 |
+
"step": 760
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 48.12,
|
| 626 |
+
"eval_loss": 1.2865585088729858,
|
| 627 |
+
"eval_micro_f1": 0.78349282246557,
|
| 628 |
+
"eval_runtime": 1.2521,
|
| 629 |
+
"eval_samples_per_second": 667.703,
|
| 630 |
+
"step": 770
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 48.75,
|
| 634 |
+
"eval_loss": 1.279433012008667,
|
| 635 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 636 |
+
"eval_runtime": 1.2416,
|
| 637 |
+
"eval_samples_per_second": 673.34,
|
| 638 |
+
"step": 780
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 49.38,
|
| 642 |
+
"eval_loss": 1.1663239002227783,
|
| 643 |
+
"eval_micro_f1": 0.801435406197606,
|
| 644 |
+
"eval_runtime": 0.8824,
|
| 645 |
+
"eval_samples_per_second": 947.447,
|
| 646 |
+
"step": 790
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 50.0,
|
| 650 |
+
"eval_loss": 1.2201182842254639,
|
| 651 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 652 |
+
"eval_runtime": 1.209,
|
| 653 |
+
"eval_samples_per_second": 691.487,
|
| 654 |
+
"step": 800
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 50.62,
|
| 658 |
+
"eval_loss": 1.2731646299362183,
|
| 659 |
+
"eval_micro_f1": 0.7799043057191627,
|
| 660 |
+
"eval_runtime": 1.1798,
|
| 661 |
+
"eval_samples_per_second": 708.603,
|
| 662 |
+
"step": 810
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 51.25,
|
| 666 |
+
"eval_loss": 1.281266689300537,
|
| 667 |
+
"eval_micro_f1": 0.7870813392119771,
|
| 668 |
+
"eval_runtime": 1.2611,
|
| 669 |
+
"eval_samples_per_second": 662.933,
|
| 670 |
+
"step": 820
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 51.88,
|
| 674 |
+
"eval_loss": 1.2305707931518555,
|
| 675 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 676 |
+
"eval_runtime": 1.2303,
|
| 677 |
+
"eval_samples_per_second": 679.521,
|
| 678 |
+
"step": 830
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 52.5,
|
| 682 |
+
"eval_loss": 1.2005953788757324,
|
| 683 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 684 |
+
"eval_runtime": 0.8744,
|
| 685 |
+
"eval_samples_per_second": 956.054,
|
| 686 |
+
"step": 840
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 53.12,
|
| 690 |
+
"eval_loss": 1.1868442296981812,
|
| 691 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 692 |
+
"eval_runtime": 1.2462,
|
| 693 |
+
"eval_samples_per_second": 670.838,
|
| 694 |
+
"step": 850
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 53.75,
|
| 698 |
+
"eval_loss": 1.1953299045562744,
|
| 699 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 700 |
+
"eval_runtime": 1.2115,
|
| 701 |
+
"eval_samples_per_second": 690.074,
|
| 702 |
+
"step": 860
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 54.38,
|
| 706 |
+
"eval_loss": 1.2319210767745972,
|
| 707 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 708 |
+
"eval_runtime": 1.293,
|
| 709 |
+
"eval_samples_per_second": 646.538,
|
| 710 |
+
"step": 870
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 55.0,
|
| 714 |
+
"eval_loss": 1.2394708395004272,
|
| 715 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 716 |
+
"eval_runtime": 1.2712,
|
| 717 |
+
"eval_samples_per_second": 657.649,
|
| 718 |
+
"step": 880
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 55.62,
|
| 722 |
+
"eval_loss": 1.2563230991363525,
|
| 723 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 724 |
+
"eval_runtime": 0.9917,
|
| 725 |
+
"eval_samples_per_second": 842.982,
|
| 726 |
+
"step": 890
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 56.25,
|
| 730 |
+
"eval_loss": 1.228058934211731,
|
| 731 |
+
"eval_micro_f1": 0.805023922944013,
|
| 732 |
+
"eval_runtime": 1.2046,
|
| 733 |
+
"eval_samples_per_second": 693.995,
|
| 734 |
+
"step": 900
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 56.88,
|
| 738 |
+
"eval_loss": 1.1921310424804688,
|
| 739 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 740 |
+
"eval_runtime": 1.248,
|
| 741 |
+
"eval_samples_per_second": 669.888,
|
| 742 |
+
"step": 910
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 57.5,
|
| 746 |
+
"eval_loss": 1.2339122295379639,
|
| 747 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 748 |
+
"eval_runtime": 1.2206,
|
| 749 |
+
"eval_samples_per_second": 684.9,
|
| 750 |
+
"step": 920
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 58.12,
|
| 754 |
+
"eval_loss": 1.2367137670516968,
|
| 755 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 756 |
+
"eval_runtime": 1.2785,
|
| 757 |
+
"eval_samples_per_second": 653.869,
|
| 758 |
+
"step": 930
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 58.75,
|
| 762 |
+
"eval_loss": 1.2339813709259033,
|
| 763 |
+
"eval_micro_f1": 0.801435406197606,
|
| 764 |
+
"eval_runtime": 1.0677,
|
| 765 |
+
"eval_samples_per_second": 782.976,
|
| 766 |
+
"step": 940
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 59.38,
|
| 770 |
+
"eval_loss": 1.211556077003479,
|
| 771 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 772 |
+
"eval_runtime": 1.2224,
|
| 773 |
+
"eval_samples_per_second": 683.888,
|
| 774 |
+
"step": 950
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 60.0,
|
| 778 |
+
"eval_loss": 1.232566475868225,
|
| 779 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 780 |
+
"eval_runtime": 1.2448,
|
| 781 |
+
"eval_samples_per_second": 671.612,
|
| 782 |
+
"step": 960
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 60.62,
|
| 786 |
+
"eval_loss": 1.3279404640197754,
|
| 787 |
+
"eval_micro_f1": 0.7822966502167676,
|
| 788 |
+
"eval_runtime": 1.3157,
|
| 789 |
+
"eval_samples_per_second": 635.425,
|
| 790 |
+
"step": 970
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 61.25,
|
| 794 |
+
"eval_loss": 1.3272722959518433,
|
| 795 |
+
"eval_micro_f1": 0.7846889947143724,
|
| 796 |
+
"eval_runtime": 1.1899,
|
| 797 |
+
"eval_samples_per_second": 702.602,
|
| 798 |
+
"step": 980
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 61.88,
|
| 802 |
+
"eval_loss": 1.2583824396133423,
|
| 803 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 804 |
+
"eval_runtime": 0.879,
|
| 805 |
+
"eval_samples_per_second": 951.032,
|
| 806 |
+
"step": 990
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 62.5,
|
| 810 |
+
"learning_rate": 7.916666666666667e-06,
|
| 811 |
+
"loss": 0.0078,
|
| 812 |
+
"step": 1000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 62.5,
|
| 816 |
+
"eval_loss": 1.1969189643859863,
|
| 817 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 818 |
+
"eval_runtime": 1.3096,
|
| 819 |
+
"eval_samples_per_second": 638.368,
|
| 820 |
+
"step": 1000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 63.12,
|
| 824 |
+
"eval_loss": 1.1956655979156494,
|
| 825 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 826 |
+
"eval_runtime": 1.0962,
|
| 827 |
+
"eval_samples_per_second": 762.667,
|
| 828 |
+
"step": 1010
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 63.75,
|
| 832 |
+
"eval_loss": 1.2163807153701782,
|
| 833 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 834 |
+
"eval_runtime": 1.3787,
|
| 835 |
+
"eval_samples_per_second": 606.388,
|
| 836 |
+
"step": 1020
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 64.38,
|
| 840 |
+
"eval_loss": 1.210200309753418,
|
| 841 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 842 |
+
"eval_runtime": 1.2665,
|
| 843 |
+
"eval_samples_per_second": 660.086,
|
| 844 |
+
"step": 1030
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 65.0,
|
| 848 |
+
"eval_loss": 1.2128517627716064,
|
| 849 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 850 |
+
"eval_runtime": 1.2021,
|
| 851 |
+
"eval_samples_per_second": 695.431,
|
| 852 |
+
"step": 1040
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 65.62,
|
| 856 |
+
"eval_loss": 1.2162755727767944,
|
| 857 |
+
"eval_micro_f1": 0.8133971286856299,
|
| 858 |
+
"eval_runtime": 1.2565,
|
| 859 |
+
"eval_samples_per_second": 665.323,
|
| 860 |
+
"step": 1050
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 66.25,
|
| 864 |
+
"eval_loss": 1.2298272848129272,
|
| 865 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 866 |
+
"eval_runtime": 1.6232,
|
| 867 |
+
"eval_samples_per_second": 515.022,
|
| 868 |
+
"step": 1060
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 66.88,
|
| 872 |
+
"eval_loss": 1.2755159139633179,
|
| 873 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 874 |
+
"eval_runtime": 1.2261,
|
| 875 |
+
"eval_samples_per_second": 681.813,
|
| 876 |
+
"step": 1070
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 67.5,
|
| 880 |
+
"eval_loss": 1.2912817001342773,
|
| 881 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 882 |
+
"eval_runtime": 1.1591,
|
| 883 |
+
"eval_samples_per_second": 721.241,
|
| 884 |
+
"step": 1080
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 68.12,
|
| 888 |
+
"eval_loss": 1.3157159090042114,
|
| 889 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 890 |
+
"eval_runtime": 1.2387,
|
| 891 |
+
"eval_samples_per_second": 674.901,
|
| 892 |
+
"step": 1090
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 68.75,
|
| 896 |
+
"eval_loss": 1.3245816230773926,
|
| 897 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 898 |
+
"eval_runtime": 1.1908,
|
| 899 |
+
"eval_samples_per_second": 702.038,
|
| 900 |
+
"step": 1100
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 69.38,
|
| 904 |
+
"eval_loss": 1.3124953508377075,
|
| 905 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 906 |
+
"eval_runtime": 1.1483,
|
| 907 |
+
"eval_samples_per_second": 728.05,
|
| 908 |
+
"step": 1110
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 70.0,
|
| 912 |
+
"eval_loss": 1.3136175870895386,
|
| 913 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 914 |
+
"eval_runtime": 1.2297,
|
| 915 |
+
"eval_samples_per_second": 679.856,
|
| 916 |
+
"step": 1120
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 70.62,
|
| 920 |
+
"eval_loss": 1.317233681678772,
|
| 921 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 922 |
+
"eval_runtime": 1.2422,
|
| 923 |
+
"eval_samples_per_second": 673.009,
|
| 924 |
+
"step": 1130
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 71.25,
|
| 928 |
+
"eval_loss": 1.342434048652649,
|
| 929 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 930 |
+
"eval_runtime": 1.2164,
|
| 931 |
+
"eval_samples_per_second": 687.252,
|
| 932 |
+
"step": 1140
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 71.88,
|
| 936 |
+
"eval_loss": 1.3436208963394165,
|
| 937 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 938 |
+
"eval_runtime": 1.2786,
|
| 939 |
+
"eval_samples_per_second": 653.846,
|
| 940 |
+
"step": 1150
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 72.5,
|
| 944 |
+
"eval_loss": 1.338441252708435,
|
| 945 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 946 |
+
"eval_runtime": 1.2159,
|
| 947 |
+
"eval_samples_per_second": 687.582,
|
| 948 |
+
"step": 1160
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 73.12,
|
| 952 |
+
"eval_loss": 1.3312480449676514,
|
| 953 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 954 |
+
"eval_runtime": 1.2921,
|
| 955 |
+
"eval_samples_per_second": 647.025,
|
| 956 |
+
"step": 1170
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 73.75,
|
| 960 |
+
"eval_loss": 1.3264278173446655,
|
| 961 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 962 |
+
"eval_runtime": 3.9896,
|
| 963 |
+
"eval_samples_per_second": 209.544,
|
| 964 |
+
"step": 1180
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 74.38,
|
| 968 |
+
"eval_loss": 1.3332304954528809,
|
| 969 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 970 |
+
"eval_runtime": 1.2124,
|
| 971 |
+
"eval_samples_per_second": 689.539,
|
| 972 |
+
"step": 1190
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 75.0,
|
| 976 |
+
"eval_loss": 1.2966439723968506,
|
| 977 |
+
"eval_micro_f1": 0.801435406197606,
|
| 978 |
+
"eval_runtime": 0.8752,
|
| 979 |
+
"eval_samples_per_second": 955.179,
|
| 980 |
+
"step": 1200
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 75.62,
|
| 984 |
+
"eval_loss": 1.2809137105941772,
|
| 985 |
+
"eval_micro_f1": 0.801435406197606,
|
| 986 |
+
"eval_runtime": 1.2334,
|
| 987 |
+
"eval_samples_per_second": 677.811,
|
| 988 |
+
"step": 1210
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 76.25,
|
| 992 |
+
"eval_loss": 1.2974853515625,
|
| 993 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 994 |
+
"eval_runtime": 1.233,
|
| 995 |
+
"eval_samples_per_second": 678.032,
|
| 996 |
+
"step": 1220
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 76.88,
|
| 1000 |
+
"eval_loss": 1.310535192489624,
|
| 1001 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 1002 |
+
"eval_runtime": 1.2405,
|
| 1003 |
+
"eval_samples_per_second": 673.936,
|
| 1004 |
+
"step": 1230
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 77.5,
|
| 1008 |
+
"eval_loss": 1.3318800926208496,
|
| 1009 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 1010 |
+
"eval_runtime": 1.2634,
|
| 1011 |
+
"eval_samples_per_second": 661.702,
|
| 1012 |
+
"step": 1240
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 78.12,
|
| 1016 |
+
"eval_loss": 1.3147168159484863,
|
| 1017 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 1018 |
+
"eval_runtime": 0.8772,
|
| 1019 |
+
"eval_samples_per_second": 953.073,
|
| 1020 |
+
"step": 1250
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 78.75,
|
| 1024 |
+
"eval_loss": 1.2976956367492676,
|
| 1025 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1026 |
+
"eval_runtime": 1.264,
|
| 1027 |
+
"eval_samples_per_second": 661.391,
|
| 1028 |
+
"step": 1260
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 79.38,
|
| 1032 |
+
"eval_loss": 1.3273509740829468,
|
| 1033 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1034 |
+
"eval_runtime": 1.2445,
|
| 1035 |
+
"eval_samples_per_second": 671.777,
|
| 1036 |
+
"step": 1270
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 80.0,
|
| 1040 |
+
"eval_loss": 1.3371427059173584,
|
| 1041 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 1042 |
+
"eval_runtime": 1.2894,
|
| 1043 |
+
"eval_samples_per_second": 648.368,
|
| 1044 |
+
"step": 1280
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 80.62,
|
| 1048 |
+
"eval_loss": 1.327476143836975,
|
| 1049 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1050 |
+
"eval_runtime": 1.2422,
|
| 1051 |
+
"eval_samples_per_second": 673.01,
|
| 1052 |
+
"step": 1290
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 81.25,
|
| 1056 |
+
"eval_loss": 1.3186708688735962,
|
| 1057 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1058 |
+
"eval_runtime": 0.8785,
|
| 1059 |
+
"eval_samples_per_second": 951.656,
|
| 1060 |
+
"step": 1300
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 81.88,
|
| 1064 |
+
"eval_loss": 1.332135796546936,
|
| 1065 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1066 |
+
"eval_runtime": 1.2523,
|
| 1067 |
+
"eval_samples_per_second": 667.587,
|
| 1068 |
+
"step": 1310
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 82.5,
|
| 1072 |
+
"eval_loss": 1.318489909172058,
|
| 1073 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1074 |
+
"eval_runtime": 1.2698,
|
| 1075 |
+
"eval_samples_per_second": 658.368,
|
| 1076 |
+
"step": 1320
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 83.12,
|
| 1080 |
+
"eval_loss": 1.2983919382095337,
|
| 1081 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1082 |
+
"eval_runtime": 1.2359,
|
| 1083 |
+
"eval_samples_per_second": 676.443,
|
| 1084 |
+
"step": 1330
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 83.75,
|
| 1088 |
+
"eval_loss": 1.291175365447998,
|
| 1089 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1090 |
+
"eval_runtime": 1.1857,
|
| 1091 |
+
"eval_samples_per_second": 705.057,
|
| 1092 |
+
"step": 1340
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 84.38,
|
| 1096 |
+
"eval_loss": 1.2960314750671387,
|
| 1097 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 1098 |
+
"eval_runtime": 0.8815,
|
| 1099 |
+
"eval_samples_per_second": 948.384,
|
| 1100 |
+
"step": 1350
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 85.0,
|
| 1104 |
+
"eval_loss": 1.3666927814483643,
|
| 1105 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 1106 |
+
"eval_runtime": 1.2997,
|
| 1107 |
+
"eval_samples_per_second": 643.203,
|
| 1108 |
+
"step": 1360
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 85.62,
|
| 1112 |
+
"eval_loss": 1.4970866441726685,
|
| 1113 |
+
"eval_micro_f1": 0.7667464109823364,
|
| 1114 |
+
"eval_runtime": 1.2654,
|
| 1115 |
+
"eval_samples_per_second": 660.663,
|
| 1116 |
+
"step": 1370
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 86.25,
|
| 1120 |
+
"eval_loss": 1.5397878885269165,
|
| 1121 |
+
"eval_micro_f1": 0.7643540664847316,
|
| 1122 |
+
"eval_runtime": 1.1787,
|
| 1123 |
+
"eval_samples_per_second": 709.241,
|
| 1124 |
+
"step": 1380
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 86.88,
|
| 1128 |
+
"eval_loss": 1.39130437374115,
|
| 1129 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 1130 |
+
"eval_runtime": 1.2669,
|
| 1131 |
+
"eval_samples_per_second": 659.895,
|
| 1132 |
+
"step": 1390
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 87.5,
|
| 1136 |
+
"eval_loss": 1.2624567747116089,
|
| 1137 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 1138 |
+
"eval_runtime": 0.8738,
|
| 1139 |
+
"eval_samples_per_second": 956.757,
|
| 1140 |
+
"step": 1400
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 88.12,
|
| 1144 |
+
"eval_loss": 1.2743109464645386,
|
| 1145 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 1146 |
+
"eval_runtime": 1.284,
|
| 1147 |
+
"eval_samples_per_second": 651.102,
|
| 1148 |
+
"step": 1410
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 88.75,
|
| 1152 |
+
"eval_loss": 1.2854809761047363,
|
| 1153 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1154 |
+
"eval_runtime": 1.2065,
|
| 1155 |
+
"eval_samples_per_second": 692.911,
|
| 1156 |
+
"step": 1420
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 89.38,
|
| 1160 |
+
"eval_loss": 1.327154278755188,
|
| 1161 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1162 |
+
"eval_runtime": 1.1934,
|
| 1163 |
+
"eval_samples_per_second": 700.519,
|
| 1164 |
+
"step": 1430
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 90.0,
|
| 1168 |
+
"eval_loss": 1.3507665395736694,
|
| 1169 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 1170 |
+
"eval_runtime": 1.2239,
|
| 1171 |
+
"eval_samples_per_second": 683.074,
|
| 1172 |
+
"step": 1440
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 90.62,
|
| 1176 |
+
"eval_loss": 1.2883785963058472,
|
| 1177 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1178 |
+
"eval_runtime": 0.8728,
|
| 1179 |
+
"eval_samples_per_second": 957.881,
|
| 1180 |
+
"step": 1450
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 91.25,
|
| 1184 |
+
"eval_loss": 1.2497007846832275,
|
| 1185 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 1186 |
+
"eval_runtime": 1.3123,
|
| 1187 |
+
"eval_samples_per_second": 637.046,
|
| 1188 |
+
"step": 1460
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 91.88,
|
| 1192 |
+
"eval_loss": 1.2521108388900757,
|
| 1193 |
+
"eval_micro_f1": 0.8145933009344323,
|
| 1194 |
+
"eval_runtime": 1.1754,
|
| 1195 |
+
"eval_samples_per_second": 711.23,
|
| 1196 |
+
"step": 1470
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 92.5,
|
| 1200 |
+
"eval_loss": 1.2865349054336548,
|
| 1201 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 1202 |
+
"eval_runtime": 1.2551,
|
| 1203 |
+
"eval_samples_per_second": 666.106,
|
| 1204 |
+
"step": 1480
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 93.12,
|
| 1208 |
+
"eval_loss": 1.3087444305419922,
|
| 1209 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1210 |
+
"eval_runtime": 1.1018,
|
| 1211 |
+
"eval_samples_per_second": 758.737,
|
| 1212 |
+
"step": 1490
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 93.75,
|
| 1216 |
+
"learning_rate": 6.875e-06,
|
| 1217 |
+
"loss": 0.0051,
|
| 1218 |
+
"step": 1500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 93.75,
|
| 1222 |
+
"eval_loss": 1.3142979145050049,
|
| 1223 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1224 |
+
"eval_runtime": 0.8803,
|
| 1225 |
+
"eval_samples_per_second": 949.724,
|
| 1226 |
+
"step": 1500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 94.38,
|
| 1230 |
+
"eval_loss": 1.2547414302825928,
|
| 1231 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 1232 |
+
"eval_runtime": 1.2904,
|
| 1233 |
+
"eval_samples_per_second": 647.886,
|
| 1234 |
+
"step": 1510
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 95.0,
|
| 1238 |
+
"eval_loss": 1.2591632604599,
|
| 1239 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1240 |
+
"eval_runtime": 1.2169,
|
| 1241 |
+
"eval_samples_per_second": 687.019,
|
| 1242 |
+
"step": 1520
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 95.62,
|
| 1246 |
+
"eval_loss": 1.2607752084732056,
|
| 1247 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1248 |
+
"eval_runtime": 1.2989,
|
| 1249 |
+
"eval_samples_per_second": 643.606,
|
| 1250 |
+
"step": 1530
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 96.25,
|
| 1254 |
+
"eval_loss": 1.292096734046936,
|
| 1255 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 1256 |
+
"eval_runtime": 1.2125,
|
| 1257 |
+
"eval_samples_per_second": 689.47,
|
| 1258 |
+
"step": 1540
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 96.88,
|
| 1262 |
+
"eval_loss": 1.3454042673110962,
|
| 1263 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1264 |
+
"eval_runtime": 1.4007,
|
| 1265 |
+
"eval_samples_per_second": 596.855,
|
| 1266 |
+
"step": 1550
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 97.5,
|
| 1270 |
+
"eval_loss": 1.3864357471466064,
|
| 1271 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 1272 |
+
"eval_runtime": 1.2241,
|
| 1273 |
+
"eval_samples_per_second": 682.938,
|
| 1274 |
+
"step": 1560
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 98.12,
|
| 1278 |
+
"eval_loss": 1.3908559083938599,
|
| 1279 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 1280 |
+
"eval_runtime": 1.3369,
|
| 1281 |
+
"eval_samples_per_second": 625.31,
|
| 1282 |
+
"step": 1570
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 98.75,
|
| 1286 |
+
"eval_loss": 1.4005109071731567,
|
| 1287 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 1288 |
+
"eval_runtime": 1.2554,
|
| 1289 |
+
"eval_samples_per_second": 665.924,
|
| 1290 |
+
"step": 1580
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 99.38,
|
| 1294 |
+
"eval_loss": 1.391554832458496,
|
| 1295 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1296 |
+
"eval_runtime": 1.2244,
|
| 1297 |
+
"eval_samples_per_second": 682.765,
|
| 1298 |
+
"step": 1590
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 100.0,
|
| 1302 |
+
"eval_loss": 1.3920481204986572,
|
| 1303 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 1304 |
+
"eval_runtime": 0.8815,
|
| 1305 |
+
"eval_samples_per_second": 948.377,
|
| 1306 |
+
"step": 1600
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 100.62,
|
| 1310 |
+
"eval_loss": 1.3875278234481812,
|
| 1311 |
+
"eval_micro_f1": 0.7930622004559891,
|
| 1312 |
+
"eval_runtime": 1.2232,
|
| 1313 |
+
"eval_samples_per_second": 683.451,
|
| 1314 |
+
"step": 1610
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 101.25,
|
| 1318 |
+
"eval_loss": 1.4043912887573242,
|
| 1319 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 1320 |
+
"eval_runtime": 1.1326,
|
| 1321 |
+
"eval_samples_per_second": 738.143,
|
| 1322 |
+
"step": 1620
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 101.88,
|
| 1326 |
+
"eval_loss": 1.4151456356048584,
|
| 1327 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 1328 |
+
"eval_runtime": 1.3225,
|
| 1329 |
+
"eval_samples_per_second": 632.123,
|
| 1330 |
+
"step": 1630
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 102.5,
|
| 1334 |
+
"eval_loss": 1.4104795455932617,
|
| 1335 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 1336 |
+
"eval_runtime": 1.2042,
|
| 1337 |
+
"eval_samples_per_second": 694.229,
|
| 1338 |
+
"step": 1640
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 103.12,
|
| 1342 |
+
"eval_loss": 1.375184178352356,
|
| 1343 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 1344 |
+
"eval_runtime": 1.1911,
|
| 1345 |
+
"eval_samples_per_second": 701.874,
|
| 1346 |
+
"step": 1650
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 103.75,
|
| 1350 |
+
"eval_loss": 1.3621584177017212,
|
| 1351 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1352 |
+
"eval_runtime": 1.2147,
|
| 1353 |
+
"eval_samples_per_second": 688.226,
|
| 1354 |
+
"step": 1660
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 104.38,
|
| 1358 |
+
"eval_loss": 1.3727388381958008,
|
| 1359 |
+
"eval_micro_f1": 0.801435406197606,
|
| 1360 |
+
"eval_runtime": 1.209,
|
| 1361 |
+
"eval_samples_per_second": 691.473,
|
| 1362 |
+
"step": 1670
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 105.0,
|
| 1366 |
+
"eval_loss": 1.380932331085205,
|
| 1367 |
+
"eval_micro_f1": 0.801435406197606,
|
| 1368 |
+
"eval_runtime": 1.2641,
|
| 1369 |
+
"eval_samples_per_second": 661.316,
|
| 1370 |
+
"step": 1680
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 105.62,
|
| 1374 |
+
"eval_loss": 1.3932331800460815,
|
| 1375 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1376 |
+
"eval_runtime": 1.2238,
|
| 1377 |
+
"eval_samples_per_second": 683.116,
|
| 1378 |
+
"step": 1690
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 106.25,
|
| 1382 |
+
"eval_loss": 1.3928004503250122,
|
| 1383 |
+
"eval_micro_f1": 0.7966507172023963,
|
| 1384 |
+
"eval_runtime": 1.1965,
|
| 1385 |
+
"eval_samples_per_second": 698.711,
|
| 1386 |
+
"step": 1700
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 106.88,
|
| 1390 |
+
"eval_loss": 1.3964753150939941,
|
| 1391 |
+
"eval_micro_f1": 0.7954545449535938,
|
| 1392 |
+
"eval_runtime": 0.8771,
|
| 1393 |
+
"eval_samples_per_second": 953.152,
|
| 1394 |
+
"step": 1710
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 107.5,
|
| 1398 |
+
"eval_loss": 1.386148452758789,
|
| 1399 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1400 |
+
"eval_runtime": 1.2205,
|
| 1401 |
+
"eval_samples_per_second": 684.952,
|
| 1402 |
+
"step": 1720
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 108.12,
|
| 1406 |
+
"eval_loss": 1.3845064640045166,
|
| 1407 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1408 |
+
"eval_runtime": 1.2444,
|
| 1409 |
+
"eval_samples_per_second": 671.803,
|
| 1410 |
+
"step": 1730
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 108.75,
|
| 1414 |
+
"eval_loss": 1.3763731718063354,
|
| 1415 |
+
"eval_micro_f1": 0.801435406197606,
|
| 1416 |
+
"eval_runtime": 1.3141,
|
| 1417 |
+
"eval_samples_per_second": 636.162,
|
| 1418 |
+
"step": 1740
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 109.38,
|
| 1422 |
+
"eval_loss": 1.377465844154358,
|
| 1423 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1424 |
+
"eval_runtime": 1.2303,
|
| 1425 |
+
"eval_samples_per_second": 679.51,
|
| 1426 |
+
"step": 1750
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 110.0,
|
| 1430 |
+
"eval_loss": 1.3758480548858643,
|
| 1431 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1432 |
+
"eval_runtime": 0.8807,
|
| 1433 |
+
"eval_samples_per_second": 949.229,
|
| 1434 |
+
"step": 1760
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 110.62,
|
| 1438 |
+
"eval_loss": 1.3523021936416626,
|
| 1439 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1440 |
+
"eval_runtime": 1.5753,
|
| 1441 |
+
"eval_samples_per_second": 530.681,
|
| 1442 |
+
"step": 1770
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 111.25,
|
| 1446 |
+
"eval_loss": 1.3379099369049072,
|
| 1447 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1448 |
+
"eval_runtime": 1.2925,
|
| 1449 |
+
"eval_samples_per_second": 646.831,
|
| 1450 |
+
"step": 1780
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 111.88,
|
| 1454 |
+
"eval_loss": 1.3364219665527344,
|
| 1455 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 1456 |
+
"eval_runtime": 1.2079,
|
| 1457 |
+
"eval_samples_per_second": 692.136,
|
| 1458 |
+
"step": 1790
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 112.5,
|
| 1462 |
+
"eval_loss": 1.3755286931991577,
|
| 1463 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 1464 |
+
"eval_runtime": 1.242,
|
| 1465 |
+
"eval_samples_per_second": 673.103,
|
| 1466 |
+
"step": 1800
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 113.12,
|
| 1470 |
+
"eval_loss": 1.3941314220428467,
|
| 1471 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1472 |
+
"eval_runtime": 0.8774,
|
| 1473 |
+
"eval_samples_per_second": 952.794,
|
| 1474 |
+
"step": 1810
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 113.75,
|
| 1478 |
+
"eval_loss": 1.3608207702636719,
|
| 1479 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1480 |
+
"eval_runtime": 1.225,
|
| 1481 |
+
"eval_samples_per_second": 682.462,
|
| 1482 |
+
"step": 1820
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 114.38,
|
| 1486 |
+
"eval_loss": 1.363614797592163,
|
| 1487 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1488 |
+
"eval_runtime": 1.2034,
|
| 1489 |
+
"eval_samples_per_second": 694.715,
|
| 1490 |
+
"step": 1830
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 115.0,
|
| 1494 |
+
"eval_loss": 1.3695135116577148,
|
| 1495 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1496 |
+
"eval_runtime": 1.2559,
|
| 1497 |
+
"eval_samples_per_second": 665.647,
|
| 1498 |
+
"step": 1840
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 115.62,
|
| 1502 |
+
"eval_loss": 1.3885483741760254,
|
| 1503 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1504 |
+
"eval_runtime": 1.2092,
|
| 1505 |
+
"eval_samples_per_second": 691.391,
|
| 1506 |
+
"step": 1850
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 116.25,
|
| 1510 |
+
"eval_loss": 1.3952767848968506,
|
| 1511 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1512 |
+
"eval_runtime": 0.8801,
|
| 1513 |
+
"eval_samples_per_second": 949.859,
|
| 1514 |
+
"step": 1860
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 116.88,
|
| 1518 |
+
"eval_loss": 1.4006528854370117,
|
| 1519 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1520 |
+
"eval_runtime": 1.2331,
|
| 1521 |
+
"eval_samples_per_second": 677.969,
|
| 1522 |
+
"step": 1870
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 117.5,
|
| 1526 |
+
"eval_loss": 1.4018462896347046,
|
| 1527 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1528 |
+
"eval_runtime": 1.214,
|
| 1529 |
+
"eval_samples_per_second": 688.636,
|
| 1530 |
+
"step": 1880
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 118.12,
|
| 1534 |
+
"eval_loss": 1.3956125974655151,
|
| 1535 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1536 |
+
"eval_runtime": 1.2698,
|
| 1537 |
+
"eval_samples_per_second": 658.395,
|
| 1538 |
+
"step": 1890
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 118.75,
|
| 1542 |
+
"eval_loss": 1.399295449256897,
|
| 1543 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1544 |
+
"eval_runtime": 1.1873,
|
| 1545 |
+
"eval_samples_per_second": 704.098,
|
| 1546 |
+
"step": 1900
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 119.38,
|
| 1550 |
+
"eval_loss": 1.3782769441604614,
|
| 1551 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 1552 |
+
"eval_runtime": 0.8736,
|
| 1553 |
+
"eval_samples_per_second": 957.009,
|
| 1554 |
+
"step": 1910
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 120.0,
|
| 1558 |
+
"eval_loss": 1.3840773105621338,
|
| 1559 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1560 |
+
"eval_runtime": 1.3233,
|
| 1561 |
+
"eval_samples_per_second": 631.744,
|
| 1562 |
+
"step": 1920
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 120.62,
|
| 1566 |
+
"eval_loss": 1.3932669162750244,
|
| 1567 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1568 |
+
"eval_runtime": 1.1049,
|
| 1569 |
+
"eval_samples_per_second": 756.626,
|
| 1570 |
+
"step": 1930
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 121.25,
|
| 1574 |
+
"eval_loss": 1.4053575992584229,
|
| 1575 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1576 |
+
"eval_runtime": 1.2271,
|
| 1577 |
+
"eval_samples_per_second": 681.275,
|
| 1578 |
+
"step": 1940
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 121.88,
|
| 1582 |
+
"eval_loss": 1.4166978597640991,
|
| 1583 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1584 |
+
"eval_runtime": 1.2483,
|
| 1585 |
+
"eval_samples_per_second": 669.695,
|
| 1586 |
+
"step": 1950
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 122.5,
|
| 1590 |
+
"eval_loss": 1.4135366678237915,
|
| 1591 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1592 |
+
"eval_runtime": 0.8725,
|
| 1593 |
+
"eval_samples_per_second": 958.127,
|
| 1594 |
+
"step": 1960
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 123.12,
|
| 1598 |
+
"eval_loss": 1.4139994382858276,
|
| 1599 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1600 |
+
"eval_runtime": 1.2175,
|
| 1601 |
+
"eval_samples_per_second": 686.667,
|
| 1602 |
+
"step": 1970
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 123.75,
|
| 1606 |
+
"eval_loss": 1.4165161848068237,
|
| 1607 |
+
"eval_micro_f1": 0.801435406197606,
|
| 1608 |
+
"eval_runtime": 1.3362,
|
| 1609 |
+
"eval_samples_per_second": 625.641,
|
| 1610 |
+
"step": 1980
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 124.38,
|
| 1614 |
+
"eval_loss": 1.40915846824646,
|
| 1615 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1616 |
+
"eval_runtime": 1.2142,
|
| 1617 |
+
"eval_samples_per_second": 688.537,
|
| 1618 |
+
"step": 1990
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 125.0,
|
| 1622 |
+
"learning_rate": 5.833333333333334e-06,
|
| 1623 |
+
"loss": 0.0044,
|
| 1624 |
+
"step": 2000
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 125.0,
|
| 1628 |
+
"eval_loss": 1.4081146717071533,
|
| 1629 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1630 |
+
"eval_runtime": 1.2318,
|
| 1631 |
+
"eval_samples_per_second": 678.656,
|
| 1632 |
+
"step": 2000
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 125.62,
|
| 1636 |
+
"eval_loss": 1.4219191074371338,
|
| 1637 |
+
"eval_micro_f1": 0.7990430617000013,
|
| 1638 |
+
"eval_runtime": 0.8813,
|
| 1639 |
+
"eval_samples_per_second": 948.645,
|
| 1640 |
+
"step": 2010
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 126.25,
|
| 1644 |
+
"eval_loss": 1.3743187189102173,
|
| 1645 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1646 |
+
"eval_runtime": 1.2439,
|
| 1647 |
+
"eval_samples_per_second": 672.106,
|
| 1648 |
+
"step": 2020
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 126.88,
|
| 1652 |
+
"eval_loss": 1.362810492515564,
|
| 1653 |
+
"eval_micro_f1": 0.8145933009344323,
|
| 1654 |
+
"eval_runtime": 1.1987,
|
| 1655 |
+
"eval_samples_per_second": 697.407,
|
| 1656 |
+
"step": 2030
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 127.5,
|
| 1660 |
+
"eval_loss": 1.3660919666290283,
|
| 1661 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 1662 |
+
"eval_runtime": 1.2816,
|
| 1663 |
+
"eval_samples_per_second": 652.291,
|
| 1664 |
+
"step": 2040
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 128.12,
|
| 1668 |
+
"eval_loss": 1.3641290664672852,
|
| 1669 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1670 |
+
"eval_runtime": 1.225,
|
| 1671 |
+
"eval_samples_per_second": 682.466,
|
| 1672 |
+
"step": 2050
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 128.75,
|
| 1676 |
+
"eval_loss": 1.3647525310516357,
|
| 1677 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 1678 |
+
"eval_runtime": 1.2187,
|
| 1679 |
+
"eval_samples_per_second": 685.983,
|
| 1680 |
+
"step": 2060
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 129.38,
|
| 1684 |
+
"eval_loss": 1.360830307006836,
|
| 1685 |
+
"eval_micro_f1": 0.8133971286856299,
|
| 1686 |
+
"eval_runtime": 1.2278,
|
| 1687 |
+
"eval_samples_per_second": 680.892,
|
| 1688 |
+
"step": 2070
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 130.0,
|
| 1692 |
+
"eval_loss": 1.3614624738693237,
|
| 1693 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 1694 |
+
"eval_runtime": 1.2841,
|
| 1695 |
+
"eval_samples_per_second": 651.062,
|
| 1696 |
+
"step": 2080
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 130.62,
|
| 1700 |
+
"eval_loss": 1.3574117422103882,
|
| 1701 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 1702 |
+
"eval_runtime": 1.7015,
|
| 1703 |
+
"eval_samples_per_second": 491.32,
|
| 1704 |
+
"step": 2090
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 131.25,
|
| 1708 |
+
"eval_loss": 1.374392032623291,
|
| 1709 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 1710 |
+
"eval_runtime": 1.2828,
|
| 1711 |
+
"eval_samples_per_second": 651.707,
|
| 1712 |
+
"step": 2100
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 131.88,
|
| 1716 |
+
"eval_loss": 1.382655143737793,
|
| 1717 |
+
"eval_micro_f1": 0.8122009564368274,
|
| 1718 |
+
"eval_runtime": 1.1275,
|
| 1719 |
+
"eval_samples_per_second": 741.461,
|
| 1720 |
+
"step": 2110
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 132.5,
|
| 1724 |
+
"eval_loss": 1.3805127143859863,
|
| 1725 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1726 |
+
"eval_runtime": 0.8758,
|
| 1727 |
+
"eval_samples_per_second": 954.57,
|
| 1728 |
+
"step": 2120
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 133.12,
|
| 1732 |
+
"eval_loss": 1.375221848487854,
|
| 1733 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1734 |
+
"eval_runtime": 1.2774,
|
| 1735 |
+
"eval_samples_per_second": 654.464,
|
| 1736 |
+
"step": 2130
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 133.75,
|
| 1740 |
+
"eval_loss": 1.402666449546814,
|
| 1741 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1742 |
+
"eval_runtime": 1.2807,
|
| 1743 |
+
"eval_samples_per_second": 652.791,
|
| 1744 |
+
"step": 2140
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 134.38,
|
| 1748 |
+
"eval_loss": 1.459406852722168,
|
| 1749 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 1750 |
+
"eval_runtime": 1.2372,
|
| 1751 |
+
"eval_samples_per_second": 675.744,
|
| 1752 |
+
"step": 2150
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 135.0,
|
| 1756 |
+
"eval_loss": 1.4087191820144653,
|
| 1757 |
+
"eval_micro_f1": 0.7978468894511987,
|
| 1758 |
+
"eval_runtime": 1.1993,
|
| 1759 |
+
"eval_samples_per_second": 697.101,
|
| 1760 |
+
"step": 2160
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 135.62,
|
| 1764 |
+
"eval_loss": 1.3900821208953857,
|
| 1765 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1766 |
+
"eval_runtime": 0.879,
|
| 1767 |
+
"eval_samples_per_second": 951.107,
|
| 1768 |
+
"step": 2170
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 136.25,
|
| 1772 |
+
"eval_loss": 1.3888801336288452,
|
| 1773 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1774 |
+
"eval_runtime": 1.2747,
|
| 1775 |
+
"eval_samples_per_second": 655.835,
|
| 1776 |
+
"step": 2180
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 136.88,
|
| 1780 |
+
"eval_loss": 1.3903478384017944,
|
| 1781 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1782 |
+
"eval_runtime": 1.6856,
|
| 1783 |
+
"eval_samples_per_second": 495.974,
|
| 1784 |
+
"step": 2190
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 137.5,
|
| 1788 |
+
"eval_loss": 1.416823387145996,
|
| 1789 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1790 |
+
"eval_runtime": 1.2675,
|
| 1791 |
+
"eval_samples_per_second": 659.555,
|
| 1792 |
+
"step": 2200
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 138.12,
|
| 1796 |
+
"eval_loss": 1.4222781658172607,
|
| 1797 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1798 |
+
"eval_runtime": 1.22,
|
| 1799 |
+
"eval_samples_per_second": 685.227,
|
| 1800 |
+
"step": 2210
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 138.75,
|
| 1804 |
+
"eval_loss": 1.4133540391921997,
|
| 1805 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1806 |
+
"eval_runtime": 0.8706,
|
| 1807 |
+
"eval_samples_per_second": 960.266,
|
| 1808 |
+
"step": 2220
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 139.38,
|
| 1812 |
+
"eval_loss": 1.426302194595337,
|
| 1813 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1814 |
+
"eval_runtime": 1.1725,
|
| 1815 |
+
"eval_samples_per_second": 713.02,
|
| 1816 |
+
"step": 2230
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 140.0,
|
| 1820 |
+
"eval_loss": 1.486598014831543,
|
| 1821 |
+
"eval_micro_f1": 0.7942583727047915,
|
| 1822 |
+
"eval_runtime": 1.1361,
|
| 1823 |
+
"eval_samples_per_second": 735.872,
|
| 1824 |
+
"step": 2240
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 140.62,
|
| 1828 |
+
"eval_loss": 1.4972662925720215,
|
| 1829 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 1830 |
+
"eval_runtime": 1.2368,
|
| 1831 |
+
"eval_samples_per_second": 675.944,
|
| 1832 |
+
"step": 2250
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 141.25,
|
| 1836 |
+
"eval_loss": 1.5124529600143433,
|
| 1837 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 1838 |
+
"eval_runtime": 1.324,
|
| 1839 |
+
"eval_samples_per_second": 631.433,
|
| 1840 |
+
"step": 2260
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 141.88,
|
| 1844 |
+
"eval_loss": 1.5166574716567993,
|
| 1845 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 1846 |
+
"eval_runtime": 0.9232,
|
| 1847 |
+
"eval_samples_per_second": 905.575,
|
| 1848 |
+
"step": 2270
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 142.5,
|
| 1852 |
+
"eval_loss": 1.5198700428009033,
|
| 1853 |
+
"eval_micro_f1": 0.7882775114607795,
|
| 1854 |
+
"eval_runtime": 1.2257,
|
| 1855 |
+
"eval_samples_per_second": 682.035,
|
| 1856 |
+
"step": 2280
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 143.12,
|
| 1860 |
+
"eval_loss": 1.506667137145996,
|
| 1861 |
+
"eval_micro_f1": 0.7894736837095819,
|
| 1862 |
+
"eval_runtime": 1.2551,
|
| 1863 |
+
"eval_samples_per_second": 666.058,
|
| 1864 |
+
"step": 2290
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 143.75,
|
| 1868 |
+
"eval_loss": 1.353083610534668,
|
| 1869 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1870 |
+
"eval_runtime": 1.2243,
|
| 1871 |
+
"eval_samples_per_second": 682.853,
|
| 1872 |
+
"step": 2300
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 144.38,
|
| 1876 |
+
"eval_loss": 1.3727068901062012,
|
| 1877 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1878 |
+
"eval_runtime": 1.1611,
|
| 1879 |
+
"eval_samples_per_second": 720.002,
|
| 1880 |
+
"step": 2310
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 145.0,
|
| 1884 |
+
"eval_loss": 1.3860739469528198,
|
| 1885 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1886 |
+
"eval_runtime": 1.3389,
|
| 1887 |
+
"eval_samples_per_second": 624.39,
|
| 1888 |
+
"step": 2320
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 145.62,
|
| 1892 |
+
"eval_loss": 1.3961546421051025,
|
| 1893 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1894 |
+
"eval_runtime": 1.2503,
|
| 1895 |
+
"eval_samples_per_second": 668.664,
|
| 1896 |
+
"step": 2330
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 146.25,
|
| 1900 |
+
"eval_loss": 1.398186206817627,
|
| 1901 |
+
"eval_micro_f1": 0.805023922944013,
|
| 1902 |
+
"eval_runtime": 1.2663,
|
| 1903 |
+
"eval_samples_per_second": 660.17,
|
| 1904 |
+
"step": 2340
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 146.88,
|
| 1908 |
+
"eval_loss": 1.3962750434875488,
|
| 1909 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1910 |
+
"eval_runtime": 1.2418,
|
| 1911 |
+
"eval_samples_per_second": 673.193,
|
| 1912 |
+
"step": 2350
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 147.5,
|
| 1916 |
+
"eval_loss": 1.4075311422348022,
|
| 1917 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1918 |
+
"eval_runtime": 1.2555,
|
| 1919 |
+
"eval_samples_per_second": 665.849,
|
| 1920 |
+
"step": 2360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 148.12,
|
| 1924 |
+
"eval_loss": 1.4148565530776978,
|
| 1925 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 1926 |
+
"eval_runtime": 1.1998,
|
| 1927 |
+
"eval_samples_per_second": 696.769,
|
| 1928 |
+
"step": 2370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 148.75,
|
| 1932 |
+
"eval_loss": 1.424800157546997,
|
| 1933 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 1934 |
+
"eval_runtime": 0.8731,
|
| 1935 |
+
"eval_samples_per_second": 957.508,
|
| 1936 |
+
"step": 2380
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 149.38,
|
| 1940 |
+
"eval_loss": 1.417323112487793,
|
| 1941 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 1942 |
+
"eval_runtime": 1.2438,
|
| 1943 |
+
"eval_samples_per_second": 672.156,
|
| 1944 |
+
"step": 2390
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 150.0,
|
| 1948 |
+
"eval_loss": 1.4144436120986938,
|
| 1949 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 1950 |
+
"eval_runtime": 1.2261,
|
| 1951 |
+
"eval_samples_per_second": 681.846,
|
| 1952 |
+
"step": 2400
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 150.62,
|
| 1956 |
+
"eval_loss": 1.4174091815948486,
|
| 1957 |
+
"eval_micro_f1": 0.801435406197606,
|
| 1958 |
+
"eval_runtime": 1.2274,
|
| 1959 |
+
"eval_samples_per_second": 681.14,
|
| 1960 |
+
"step": 2410
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 151.25,
|
| 1964 |
+
"eval_loss": 1.413324236869812,
|
| 1965 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1966 |
+
"eval_runtime": 1.2046,
|
| 1967 |
+
"eval_samples_per_second": 694.0,
|
| 1968 |
+
"step": 2420
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 151.88,
|
| 1972 |
+
"eval_loss": 1.4170891046524048,
|
| 1973 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 1974 |
+
"eval_runtime": 0.872,
|
| 1975 |
+
"eval_samples_per_second": 958.689,
|
| 1976 |
+
"step": 2430
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 152.5,
|
| 1980 |
+
"eval_loss": 1.4190303087234497,
|
| 1981 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1982 |
+
"eval_runtime": 1.2273,
|
| 1983 |
+
"eval_samples_per_second": 681.156,
|
| 1984 |
+
"step": 2440
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 153.12,
|
| 1988 |
+
"eval_loss": 1.4272630214691162,
|
| 1989 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1990 |
+
"eval_runtime": 1.2724,
|
| 1991 |
+
"eval_samples_per_second": 657.001,
|
| 1992 |
+
"step": 2450
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 153.75,
|
| 1996 |
+
"eval_loss": 1.429481029510498,
|
| 1997 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 1998 |
+
"eval_runtime": 1.264,
|
| 1999 |
+
"eval_samples_per_second": 661.394,
|
| 2000 |
+
"step": 2460
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 154.38,
|
| 2004 |
+
"eval_loss": 1.4257972240447998,
|
| 2005 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2006 |
+
"eval_runtime": 1.1744,
|
| 2007 |
+
"eval_samples_per_second": 711.853,
|
| 2008 |
+
"step": 2470
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 155.0,
|
| 2012 |
+
"eval_loss": 1.4273958206176758,
|
| 2013 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2014 |
+
"eval_runtime": 0.8805,
|
| 2015 |
+
"eval_samples_per_second": 949.424,
|
| 2016 |
+
"step": 2480
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 155.62,
|
| 2020 |
+
"eval_loss": 1.4307893514633179,
|
| 2021 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2022 |
+
"eval_runtime": 1.2578,
|
| 2023 |
+
"eval_samples_per_second": 664.629,
|
| 2024 |
+
"step": 2490
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 156.25,
|
| 2028 |
+
"learning_rate": 4.791666666666668e-06,
|
| 2029 |
+
"loss": 0.0042,
|
| 2030 |
+
"step": 2500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 156.25,
|
| 2034 |
+
"eval_loss": 1.4220995903015137,
|
| 2035 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2036 |
+
"eval_runtime": 1.2821,
|
| 2037 |
+
"eval_samples_per_second": 652.047,
|
| 2038 |
+
"step": 2500
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 156.88,
|
| 2042 |
+
"eval_loss": 1.4195088148117065,
|
| 2043 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2044 |
+
"eval_runtime": 1.2563,
|
| 2045 |
+
"eval_samples_per_second": 665.428,
|
| 2046 |
+
"step": 2510
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 157.5,
|
| 2050 |
+
"eval_loss": 1.4252077341079712,
|
| 2051 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2052 |
+
"eval_runtime": 1.3978,
|
| 2053 |
+
"eval_samples_per_second": 598.091,
|
| 2054 |
+
"step": 2520
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 158.12,
|
| 2058 |
+
"eval_loss": 1.428691029548645,
|
| 2059 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2060 |
+
"eval_runtime": 0.8787,
|
| 2061 |
+
"eval_samples_per_second": 951.381,
|
| 2062 |
+
"step": 2530
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 158.75,
|
| 2066 |
+
"eval_loss": 1.4256610870361328,
|
| 2067 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2068 |
+
"eval_runtime": 1.2302,
|
| 2069 |
+
"eval_samples_per_second": 679.563,
|
| 2070 |
+
"step": 2540
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 159.38,
|
| 2074 |
+
"eval_loss": 1.4328128099441528,
|
| 2075 |
+
"eval_micro_f1": 0.805023922944013,
|
| 2076 |
+
"eval_runtime": 1.2704,
|
| 2077 |
+
"eval_samples_per_second": 658.068,
|
| 2078 |
+
"step": 2550
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 160.0,
|
| 2082 |
+
"eval_loss": 1.4293843507766724,
|
| 2083 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2084 |
+
"eval_runtime": 1.2275,
|
| 2085 |
+
"eval_samples_per_second": 681.075,
|
| 2086 |
+
"step": 2560
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 160.62,
|
| 2090 |
+
"eval_loss": 1.4297587871551514,
|
| 2091 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2092 |
+
"eval_runtime": 0.8781,
|
| 2093 |
+
"eval_samples_per_second": 952.051,
|
| 2094 |
+
"step": 2570
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 161.25,
|
| 2098 |
+
"eval_loss": 1.4381576776504517,
|
| 2099 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2100 |
+
"eval_runtime": 0.8794,
|
| 2101 |
+
"eval_samples_per_second": 950.628,
|
| 2102 |
+
"step": 2580
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 161.88,
|
| 2106 |
+
"eval_loss": 1.439926266670227,
|
| 2107 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2108 |
+
"eval_runtime": 1.3552,
|
| 2109 |
+
"eval_samples_per_second": 616.906,
|
| 2110 |
+
"step": 2590
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 162.5,
|
| 2114 |
+
"eval_loss": 1.4571921825408936,
|
| 2115 |
+
"eval_micro_f1": 0.801435406197606,
|
| 2116 |
+
"eval_runtime": 1.2667,
|
| 2117 |
+
"eval_samples_per_second": 660.002,
|
| 2118 |
+
"step": 2600
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 163.12,
|
| 2122 |
+
"eval_loss": 1.4617875814437866,
|
| 2123 |
+
"eval_micro_f1": 0.801435406197606,
|
| 2124 |
+
"eval_runtime": 1.24,
|
| 2125 |
+
"eval_samples_per_second": 674.215,
|
| 2126 |
+
"step": 2610
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 163.75,
|
| 2130 |
+
"eval_loss": 1.4595539569854736,
|
| 2131 |
+
"eval_micro_f1": 0.801435406197606,
|
| 2132 |
+
"eval_runtime": 1.1716,
|
| 2133 |
+
"eval_samples_per_second": 713.53,
|
| 2134 |
+
"step": 2620
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 164.38,
|
| 2138 |
+
"eval_loss": 1.4529329538345337,
|
| 2139 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2140 |
+
"eval_runtime": 1.0252,
|
| 2141 |
+
"eval_samples_per_second": 815.48,
|
| 2142 |
+
"step": 2630
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 165.0,
|
| 2146 |
+
"eval_loss": 1.4418772459030151,
|
| 2147 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2148 |
+
"eval_runtime": 1.1928,
|
| 2149 |
+
"eval_samples_per_second": 700.888,
|
| 2150 |
+
"step": 2640
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 165.62,
|
| 2154 |
+
"eval_loss": 1.4406232833862305,
|
| 2155 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2156 |
+
"eval_runtime": 1.2626,
|
| 2157 |
+
"eval_samples_per_second": 662.129,
|
| 2158 |
+
"step": 2650
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 166.25,
|
| 2162 |
+
"eval_loss": 1.4389880895614624,
|
| 2163 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2164 |
+
"eval_runtime": 1.2098,
|
| 2165 |
+
"eval_samples_per_second": 691.045,
|
| 2166 |
+
"step": 2660
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 166.88,
|
| 2170 |
+
"eval_loss": 1.4397320747375488,
|
| 2171 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2172 |
+
"eval_runtime": 1.2381,
|
| 2173 |
+
"eval_samples_per_second": 675.232,
|
| 2174 |
+
"step": 2670
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 167.5,
|
| 2178 |
+
"eval_loss": 1.4551808834075928,
|
| 2179 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2180 |
+
"eval_runtime": 1.2946,
|
| 2181 |
+
"eval_samples_per_second": 645.758,
|
| 2182 |
+
"step": 2680
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 168.12,
|
| 2186 |
+
"eval_loss": 1.4501805305480957,
|
| 2187 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2188 |
+
"eval_runtime": 1.2067,
|
| 2189 |
+
"eval_samples_per_second": 692.798,
|
| 2190 |
+
"step": 2690
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 168.75,
|
| 2194 |
+
"eval_loss": 1.4495714902877808,
|
| 2195 |
+
"eval_micro_f1": 0.805023922944013,
|
| 2196 |
+
"eval_runtime": 1.2244,
|
| 2197 |
+
"eval_samples_per_second": 682.775,
|
| 2198 |
+
"step": 2700
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 169.38,
|
| 2202 |
+
"eval_loss": 1.4503188133239746,
|
| 2203 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2204 |
+
"eval_runtime": 1.3433,
|
| 2205 |
+
"eval_samples_per_second": 622.326,
|
| 2206 |
+
"step": 2710
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 170.0,
|
| 2210 |
+
"eval_loss": 1.4485152959823608,
|
| 2211 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 2212 |
+
"eval_runtime": 1.2481,
|
| 2213 |
+
"eval_samples_per_second": 669.796,
|
| 2214 |
+
"step": 2720
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 170.62,
|
| 2218 |
+
"eval_loss": 1.4404151439666748,
|
| 2219 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 2220 |
+
"eval_runtime": 1.1977,
|
| 2221 |
+
"eval_samples_per_second": 698.008,
|
| 2222 |
+
"step": 2730
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 171.25,
|
| 2226 |
+
"eval_loss": 1.4550838470458984,
|
| 2227 |
+
"eval_micro_f1": 0.8026315784464082,
|
| 2228 |
+
"eval_runtime": 1.264,
|
| 2229 |
+
"eval_samples_per_second": 661.391,
|
| 2230 |
+
"step": 2740
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 171.88,
|
| 2234 |
+
"eval_loss": 1.4467554092407227,
|
| 2235 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 2236 |
+
"eval_runtime": 1.216,
|
| 2237 |
+
"eval_samples_per_second": 687.528,
|
| 2238 |
+
"step": 2750
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 172.5,
|
| 2242 |
+
"eval_loss": 1.4552243947982788,
|
| 2243 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 2244 |
+
"eval_runtime": 1.2435,
|
| 2245 |
+
"eval_samples_per_second": 672.314,
|
| 2246 |
+
"step": 2760
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 173.12,
|
| 2250 |
+
"eval_loss": 1.456278920173645,
|
| 2251 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 2252 |
+
"eval_runtime": 1.2556,
|
| 2253 |
+
"eval_samples_per_second": 665.823,
|
| 2254 |
+
"step": 2770
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 173.75,
|
| 2258 |
+
"eval_loss": 1.4586423635482788,
|
| 2259 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 2260 |
+
"eval_runtime": 1.1702,
|
| 2261 |
+
"eval_samples_per_second": 714.398,
|
| 2262 |
+
"step": 2780
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 174.38,
|
| 2266 |
+
"eval_loss": 1.4615603685379028,
|
| 2267 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 2268 |
+
"eval_runtime": 1.2023,
|
| 2269 |
+
"eval_samples_per_second": 695.339,
|
| 2270 |
+
"step": 2790
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 175.0,
|
| 2274 |
+
"eval_loss": 1.4521640539169312,
|
| 2275 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 2276 |
+
"eval_runtime": 1.1678,
|
| 2277 |
+
"eval_samples_per_second": 715.881,
|
| 2278 |
+
"step": 2800
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 175.62,
|
| 2282 |
+
"eval_loss": 1.459039330482483,
|
| 2283 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 2284 |
+
"eval_runtime": 1.3223,
|
| 2285 |
+
"eval_samples_per_second": 632.225,
|
| 2286 |
+
"step": 2810
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 176.25,
|
| 2290 |
+
"eval_loss": 1.4770715236663818,
|
| 2291 |
+
"eval_micro_f1": 0.805023922944013,
|
| 2292 |
+
"eval_runtime": 1.5915,
|
| 2293 |
+
"eval_samples_per_second": 525.283,
|
| 2294 |
+
"step": 2820
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 176.88,
|
| 2298 |
+
"eval_loss": 1.4787960052490234,
|
| 2299 |
+
"eval_micro_f1": 0.8038277506952107,
|
| 2300 |
+
"eval_runtime": 0.9666,
|
| 2301 |
+
"eval_samples_per_second": 864.913,
|
| 2302 |
+
"step": 2830
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 177.5,
|
| 2306 |
+
"eval_loss": 1.4933847188949585,
|
| 2307 |
+
"eval_micro_f1": 0.8002392339488035,
|
| 2308 |
+
"eval_runtime": 1.1953,
|
| 2309 |
+
"eval_samples_per_second": 699.427,
|
| 2310 |
+
"step": 2840
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 178.12,
|
| 2314 |
+
"eval_loss": 1.4820541143417358,
|
| 2315 |
+
"eval_micro_f1": 0.801435406197606,
|
| 2316 |
+
"eval_runtime": 1.2387,
|
| 2317 |
+
"eval_samples_per_second": 674.92,
|
| 2318 |
+
"step": 2850
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 178.75,
|
| 2322 |
+
"eval_loss": 1.4721782207489014,
|
| 2323 |
+
"eval_micro_f1": 0.805023922944013,
|
| 2324 |
+
"eval_runtime": 1.2678,
|
| 2325 |
+
"eval_samples_per_second": 659.39,
|
| 2326 |
+
"step": 2860
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 179.38,
|
| 2330 |
+
"eval_loss": 1.4754302501678467,
|
| 2331 |
+
"eval_micro_f1": 0.805023922944013,
|
| 2332 |
+
"eval_runtime": 1.2891,
|
| 2333 |
+
"eval_samples_per_second": 648.51,
|
| 2334 |
+
"step": 2870
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 180.0,
|
| 2338 |
+
"eval_loss": 1.4293739795684814,
|
| 2339 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 2340 |
+
"eval_runtime": 1.2496,
|
| 2341 |
+
"eval_samples_per_second": 668.995,
|
| 2342 |
+
"step": 2880
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 180.62,
|
| 2346 |
+
"eval_loss": 1.4377115964889526,
|
| 2347 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 2348 |
+
"eval_runtime": 1.2049,
|
| 2349 |
+
"eval_samples_per_second": 693.81,
|
| 2350 |
+
"step": 2890
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 181.25,
|
| 2354 |
+
"eval_loss": 1.4376572370529175,
|
| 2355 |
+
"eval_micro_f1": 0.8098086119392227,
|
| 2356 |
+
"eval_runtime": 1.2023,
|
| 2357 |
+
"eval_samples_per_second": 695.357,
|
| 2358 |
+
"step": 2900
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 181.88,
|
| 2362 |
+
"eval_loss": 1.4372467994689941,
|
| 2363 |
+
"eval_micro_f1": 0.8074162674416179,
|
| 2364 |
+
"eval_runtime": 1.2237,
|
| 2365 |
+
"eval_samples_per_second": 683.176,
|
| 2366 |
+
"step": 2910
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 182.5,
|
| 2370 |
+
"eval_loss": 1.442883014678955,
|
| 2371 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 2372 |
+
"eval_runtime": 1.6226,
|
| 2373 |
+
"eval_samples_per_second": 515.219,
|
| 2374 |
+
"step": 2920
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 183.12,
|
| 2378 |
+
"eval_loss": 1.531345248222351,
|
| 2379 |
+
"eval_micro_f1": 0.7918660282071867,
|
| 2380 |
+
"eval_runtime": 1.2097,
|
| 2381 |
+
"eval_samples_per_second": 691.06,
|
| 2382 |
+
"step": 2930
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 183.75,
|
| 2386 |
+
"eval_loss": 1.5837615728378296,
|
| 2387 |
+
"eval_micro_f1": 0.7858851669631748,
|
| 2388 |
+
"eval_runtime": 0.8758,
|
| 2389 |
+
"eval_samples_per_second": 954.581,
|
| 2390 |
+
"step": 2940
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 184.38,
|
| 2394 |
+
"eval_loss": 1.5461186170578003,
|
| 2395 |
+
"eval_micro_f1": 0.7906698559583843,
|
| 2396 |
+
"eval_runtime": 0.9708,
|
| 2397 |
+
"eval_samples_per_second": 861.124,
|
| 2398 |
+
"step": 2950
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 185.0,
|
| 2402 |
+
"eval_loss": 1.4445397853851318,
|
| 2403 |
+
"eval_micro_f1": 0.8086124396904203,
|
| 2404 |
+
"eval_runtime": 1.1505,
|
| 2405 |
+
"eval_samples_per_second": 726.643,
|
| 2406 |
+
"step": 2960
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 185.62,
|
| 2410 |
+
"eval_loss": 1.4366849660873413,
|
| 2411 |
+
"eval_micro_f1": 0.8062200951928155,
|
| 2412 |
+
"eval_runtime": 1.2172,
|
| 2413 |
+
"eval_samples_per_second": 686.81,
|
| 2414 |
+
"step": 2970
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 186.25,
|
| 2418 |
+
"eval_loss": 1.4100123643875122,
|
| 2419 |
+
"eval_micro_f1": 0.8169856454320371,
|
| 2420 |
+
"eval_runtime": 1.3528,
|
| 2421 |
+
"eval_samples_per_second": 617.955,
|
| 2422 |
+
"step": 2980
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 186.88,
|
| 2426 |
+
"eval_loss": 1.415737271308899,
|
| 2427 |
+
"eval_micro_f1": 0.8110047841880251,
|
| 2428 |
+
"eval_runtime": 1.3206,
|
| 2429 |
+
"eval_samples_per_second": 633.03,
|
| 2430 |
+
"step": 2990
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 187.5,
|
| 2434 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 2435 |
+
"loss": 0.0037,
|
| 2436 |
+
"step": 3000
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 187.5,
|
| 2440 |
+
"eval_loss": 1.4148428440093994,
|
| 2441 |
+
"eval_micro_f1": 0.8205741621784443,
|
| 2442 |
+
"eval_runtime": 1.3405,
|
| 2443 |
+
"eval_samples_per_second": 623.635,
|
| 2444 |
+
"step": 3000
|
| 2445 |
+
}
|
| 2446 |
+
],
|
| 2447 |
+
"max_steps": 4800,
|
| 2448 |
+
"num_train_epochs": 300,
|
| 2449 |
+
"total_flos": 17832540398972616,
|
| 2450 |
+
"trial_name": null,
|
| 2451 |
+
"trial_params": null
|
| 2452 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab37931da584e22554fd2ddb026ce42a985ea1518ea9f6a8d61f537770bd08ca
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|