Add model files
Browse files- config.json +43 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1360 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0,
|
| 25 |
+
"LABEL_1": 1,
|
| 26 |
+
"LABEL_2": 2,
|
| 27 |
+
"LABEL_3": 3,
|
| 28 |
+
"LABEL_4": 4,
|
| 29 |
+
"LABEL_5": 5
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-05,
|
| 32 |
+
"max_position_embeddings": 514,
|
| 33 |
+
"model_type": "roberta",
|
| 34 |
+
"num_attention_heads": 16,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"pad_token_id": 1,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.19.2",
|
| 40 |
+
"type_vocab_size": 1,
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50279
|
| 43 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2826ecfc3fde5515c55279958c1d295ced0324c25d1302e7331cb00a9ced926
|
| 3 |
+
size 1417459057
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1ecff4e82abfaffa75823ae1c56d6a94d4ec804e3443e50a7694a676a3a89d
|
| 3 |
+
size 17563
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd3d052ca5be7d42b9ce31ac7a9f5853560b889a7b57f5a0757484991ba3719f
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:111a0dff40c56c0eab15e84ea1cbeee65a7baf0628e8c5b042733967f436e44f
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "padding": true, "truncation": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.06025264039635658,
|
| 3 |
+
"best_model_checkpoint": "roberta-large-finetuned-iterate_intent_classification-200k_all_extra_datasets_v2_single-task_multi-sent/checkpoint-56000",
|
| 4 |
+
"epoch": 1.5705631590756113,
|
| 5 |
+
"global_step": 56000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 2.9860612519632043e-05,
|
| 13 |
+
"loss": 0.139,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 2.9720383666143147e-05,
|
| 19 |
+
"loss": 0.0977,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"eval_accuracy": 0.971162091635854,
|
| 25 |
+
"eval_f1": 0.5399681845297277,
|
| 26 |
+
"eval_loss": 0.09991234540939331,
|
| 27 |
+
"eval_precision": 0.5387896825396825,
|
| 28 |
+
"eval_recall": 0.5411518533280192,
|
| 29 |
+
"eval_runtime": 37.2769,
|
| 30 |
+
"eval_samples_per_second": 80.479,
|
| 31 |
+
"eval_steps_per_second": 5.043,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 2.9580154812654254e-05,
|
| 37 |
+
"loss": 0.0907,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06,
|
| 42 |
+
"learning_rate": 2.943992595916536e-05,
|
| 43 |
+
"loss": 0.085,
|
| 44 |
+
"step": 2000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"eval_accuracy": 0.9737669546615523,
|
| 49 |
+
"eval_f1": 0.5691315136476427,
|
| 50 |
+
"eval_loss": 0.09658516198396683,
|
| 51 |
+
"eval_precision": 0.566936919122009,
|
| 52 |
+
"eval_recall": 0.5713431646074133,
|
| 53 |
+
"eval_runtime": 38.0964,
|
| 54 |
+
"eval_samples_per_second": 78.748,
|
| 55 |
+
"eval_steps_per_second": 4.935,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.07,
|
| 60 |
+
"learning_rate": 2.9299697105676466e-05,
|
| 61 |
+
"loss": 0.085,
|
| 62 |
+
"step": 2500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.08,
|
| 66 |
+
"learning_rate": 2.915946825218757e-05,
|
| 67 |
+
"loss": 0.0758,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"eval_accuracy": 0.9763026620317009,
|
| 73 |
+
"eval_f1": 0.6236316332040647,
|
| 74 |
+
"eval_loss": 0.07386751472949982,
|
| 75 |
+
"eval_precision": 0.6146105466860183,
|
| 76 |
+
"eval_recall": 0.6329214826624153,
|
| 77 |
+
"eval_runtime": 37.6732,
|
| 78 |
+
"eval_samples_per_second": 79.632,
|
| 79 |
+
"eval_steps_per_second": 4.99,
|
| 80 |
+
"step": 3000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1,
|
| 84 |
+
"learning_rate": 2.9019519856405656e-05,
|
| 85 |
+
"loss": 0.0781,
|
| 86 |
+
"step": 3500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11,
|
| 90 |
+
"learning_rate": 2.887929100291676e-05,
|
| 91 |
+
"loss": 0.0782,
|
| 92 |
+
"step": 4000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.11,
|
| 96 |
+
"eval_accuracy": 0.9755096771813999,
|
| 97 |
+
"eval_f1": 0.5991719984945427,
|
| 98 |
+
"eval_loss": 0.07741887867450714,
|
| 99 |
+
"eval_precision": 0.5675579322638146,
|
| 100 |
+
"eval_recall": 0.6345157433240335,
|
| 101 |
+
"eval_runtime": 36.9968,
|
| 102 |
+
"eval_samples_per_second": 81.088,
|
| 103 |
+
"eval_steps_per_second": 5.082,
|
| 104 |
+
"step": 4000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.13,
|
| 108 |
+
"learning_rate": 2.8739342607134845e-05,
|
| 109 |
+
"loss": 0.0778,
|
| 110 |
+
"step": 4500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.14,
|
| 114 |
+
"learning_rate": 2.859911375364595e-05,
|
| 115 |
+
"loss": 0.0695,
|
| 116 |
+
"step": 5000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.14,
|
| 120 |
+
"eval_accuracy": 0.9774137628975298,
|
| 121 |
+
"eval_f1": 0.680416421135337,
|
| 122 |
+
"eval_loss": 0.07352685928344727,
|
| 123 |
+
"eval_precision": 0.6707978311386522,
|
| 124 |
+
"eval_recall": 0.6903148664806696,
|
| 125 |
+
"eval_runtime": 36.5263,
|
| 126 |
+
"eval_samples_per_second": 82.133,
|
| 127 |
+
"eval_steps_per_second": 5.147,
|
| 128 |
+
"step": 5000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.15,
|
| 132 |
+
"learning_rate": 2.8458884900157057e-05,
|
| 133 |
+
"loss": 0.0699,
|
| 134 |
+
"step": 5500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.17,
|
| 138 |
+
"learning_rate": 2.8318656046668165e-05,
|
| 139 |
+
"loss": 0.0722,
|
| 140 |
+
"step": 6000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.17,
|
| 144 |
+
"eval_accuracy": 0.9802675862832062,
|
| 145 |
+
"eval_f1": 0.7195344478966317,
|
| 146 |
+
"eval_loss": 0.06846912950277328,
|
| 147 |
+
"eval_precision": 0.7123327800019529,
|
| 148 |
+
"eval_recall": 0.7268832204065365,
|
| 149 |
+
"eval_runtime": 37.6415,
|
| 150 |
+
"eval_samples_per_second": 79.699,
|
| 151 |
+
"eval_steps_per_second": 4.994,
|
| 152 |
+
"step": 6000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.18,
|
| 156 |
+
"learning_rate": 2.817842719317927e-05,
|
| 157 |
+
"loss": 0.0702,
|
| 158 |
+
"step": 6500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.2,
|
| 162 |
+
"learning_rate": 2.8038198339690376e-05,
|
| 163 |
+
"loss": 0.0667,
|
| 164 |
+
"step": 7000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2,
|
| 168 |
+
"eval_accuracy": 0.9801108334639607,
|
| 169 |
+
"eval_f1": 0.7278459189202502,
|
| 170 |
+
"eval_loss": 0.06565115600824356,
|
| 171 |
+
"eval_precision": 0.7197272284461763,
|
| 172 |
+
"eval_recall": 0.7361498605021921,
|
| 173 |
+
"eval_runtime": 37.325,
|
| 174 |
+
"eval_samples_per_second": 80.375,
|
| 175 |
+
"eval_steps_per_second": 5.037,
|
| 176 |
+
"step": 7000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.21,
|
| 180 |
+
"learning_rate": 2.789796948620148e-05,
|
| 181 |
+
"loss": 0.0658,
|
| 182 |
+
"step": 7500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.22,
|
| 186 |
+
"learning_rate": 2.7757740632712588e-05,
|
| 187 |
+
"loss": 0.0688,
|
| 188 |
+
"step": 8000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.22,
|
| 192 |
+
"eval_accuracy": 0.9796728476454805,
|
| 193 |
+
"eval_f1": 0.7163943328232216,
|
| 194 |
+
"eval_loss": 0.06845768541097641,
|
| 195 |
+
"eval_precision": 0.7099109676156932,
|
| 196 |
+
"eval_recall": 0.7229972100438422,
|
| 197 |
+
"eval_runtime": 36.6425,
|
| 198 |
+
"eval_samples_per_second": 81.872,
|
| 199 |
+
"eval_steps_per_second": 5.131,
|
| 200 |
+
"step": 8000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.24,
|
| 204 |
+
"learning_rate": 2.7617511779223692e-05,
|
| 205 |
+
"loss": 0.0678,
|
| 206 |
+
"step": 8500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.25,
|
| 210 |
+
"learning_rate": 2.7477563383441778e-05,
|
| 211 |
+
"loss": 0.0654,
|
| 212 |
+
"step": 9000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.25,
|
| 216 |
+
"eval_accuracy": 0.9798526523499091,
|
| 217 |
+
"eval_f1": 0.7101066431855984,
|
| 218 |
+
"eval_loss": 0.06661399453878403,
|
| 219 |
+
"eval_precision": 0.6974822217951182,
|
| 220 |
+
"eval_recall": 0.7231964926265444,
|
| 221 |
+
"eval_runtime": 41.9581,
|
| 222 |
+
"eval_samples_per_second": 71.5,
|
| 223 |
+
"eval_steps_per_second": 4.481,
|
| 224 |
+
"step": 9000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.27,
|
| 228 |
+
"learning_rate": 2.7337334529952882e-05,
|
| 229 |
+
"loss": 0.0691,
|
| 230 |
+
"step": 9500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.28,
|
| 234 |
+
"learning_rate": 2.7197386134170967e-05,
|
| 235 |
+
"loss": 0.0677,
|
| 236 |
+
"step": 10000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.28,
|
| 240 |
+
"eval_accuracy": 0.980018625923228,
|
| 241 |
+
"eval_f1": 0.7221836228287842,
|
| 242 |
+
"eval_loss": 0.07092269510030746,
|
| 243 |
+
"eval_precision": 0.7193988530749457,
|
| 244 |
+
"eval_recall": 0.7249900358708649,
|
| 245 |
+
"eval_runtime": 37.1023,
|
| 246 |
+
"eval_samples_per_second": 80.858,
|
| 247 |
+
"eval_steps_per_second": 5.067,
|
| 248 |
+
"step": 10000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.29,
|
| 252 |
+
"learning_rate": 2.7057157280682075e-05,
|
| 253 |
+
"loss": 0.0686,
|
| 254 |
+
"step": 10500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.31,
|
| 258 |
+
"learning_rate": 2.691692842719318e-05,
|
| 259 |
+
"loss": 0.0666,
|
| 260 |
+
"step": 11000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.31,
|
| 264 |
+
"eval_accuracy": 0.9806548579542835,
|
| 265 |
+
"eval_f1": 0.7343549184379634,
|
| 266 |
+
"eval_loss": 0.0653684139251709,
|
| 267 |
+
"eval_precision": 0.7286639199529135,
|
| 268 |
+
"eval_recall": 0.7401355121562375,
|
| 269 |
+
"eval_runtime": 35.9849,
|
| 270 |
+
"eval_samples_per_second": 83.368,
|
| 271 |
+
"eval_steps_per_second": 5.224,
|
| 272 |
+
"step": 11000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.32,
|
| 276 |
+
"learning_rate": 2.6776699573704287e-05,
|
| 277 |
+
"loss": 0.0667,
|
| 278 |
+
"step": 11500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.34,
|
| 282 |
+
"learning_rate": 2.663647072021539e-05,
|
| 283 |
+
"loss": 0.0635,
|
| 284 |
+
"step": 12000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.34,
|
| 288 |
+
"eval_accuracy": 0.9803413523157923,
|
| 289 |
+
"eval_f1": 0.7172954434100932,
|
| 290 |
+
"eval_loss": 0.06524238735437393,
|
| 291 |
+
"eval_precision": 0.7056101792943898,
|
| 292 |
+
"eval_recall": 0.7293742526903149,
|
| 293 |
+
"eval_runtime": 37.7011,
|
| 294 |
+
"eval_samples_per_second": 79.573,
|
| 295 |
+
"eval_steps_per_second": 4.987,
|
| 296 |
+
"step": 12000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.35,
|
| 300 |
+
"learning_rate": 2.6496241866726498e-05,
|
| 301 |
+
"loss": 0.066,
|
| 302 |
+
"step": 12500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.36,
|
| 306 |
+
"learning_rate": 2.6356013013237602e-05,
|
| 307 |
+
"loss": 0.0635,
|
| 308 |
+
"step": 13000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.36,
|
| 312 |
+
"eval_accuracy": 0.9800601193165577,
|
| 313 |
+
"eval_f1": 0.7266683205160009,
|
| 314 |
+
"eval_loss": 0.07080024480819702,
|
| 315 |
+
"eval_precision": 0.7236881114734658,
|
| 316 |
+
"eval_recall": 0.7296731765643683,
|
| 317 |
+
"eval_runtime": 37.3623,
|
| 318 |
+
"eval_samples_per_second": 80.295,
|
| 319 |
+
"eval_steps_per_second": 5.032,
|
| 320 |
+
"step": 13000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.38,
|
| 324 |
+
"learning_rate": 2.621578415974871e-05,
|
| 325 |
+
"loss": 0.0614,
|
| 326 |
+
"step": 13500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.39,
|
| 330 |
+
"learning_rate": 2.6075555306259814e-05,
|
| 331 |
+
"loss": 0.0619,
|
| 332 |
+
"step": 14000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.39,
|
| 336 |
+
"eval_accuracy": 0.979778886317323,
|
| 337 |
+
"eval_f1": 0.7210257933561068,
|
| 338 |
+
"eval_loss": 0.06537187844514847,
|
| 339 |
+
"eval_precision": 0.7165207123880744,
|
| 340 |
+
"eval_recall": 0.7255878836189718,
|
| 341 |
+
"eval_runtime": 37.6468,
|
| 342 |
+
"eval_samples_per_second": 79.688,
|
| 343 |
+
"eval_steps_per_second": 4.994,
|
| 344 |
+
"step": 14000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.41,
|
| 348 |
+
"learning_rate": 2.59356069104779e-05,
|
| 349 |
+
"loss": 0.0623,
|
| 350 |
+
"step": 14500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.42,
|
| 354 |
+
"learning_rate": 2.5795378056989004e-05,
|
| 355 |
+
"loss": 0.0621,
|
| 356 |
+
"step": 15000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.42,
|
| 360 |
+
"eval_accuracy": 0.9795529778425279,
|
| 361 |
+
"eval_f1": 0.7259988073941562,
|
| 362 |
+
"eval_loss": 0.07811370491981506,
|
| 363 |
+
"eval_precision": 0.7241276764472641,
|
| 364 |
+
"eval_recall": 0.7278796333200478,
|
| 365 |
+
"eval_runtime": 37.6797,
|
| 366 |
+
"eval_samples_per_second": 79.618,
|
| 367 |
+
"eval_steps_per_second": 4.989,
|
| 368 |
+
"step": 15000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.43,
|
| 372 |
+
"learning_rate": 2.565542966120709e-05,
|
| 373 |
+
"loss": 0.0663,
|
| 374 |
+
"step": 15500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.45,
|
| 378 |
+
"learning_rate": 2.5515200807718197e-05,
|
| 379 |
+
"loss": 0.0635,
|
| 380 |
+
"step": 16000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.45,
|
| 384 |
+
"eval_accuracy": 0.9805442089054043,
|
| 385 |
+
"eval_f1": 0.7281001137656427,
|
| 386 |
+
"eval_loss": 0.06664826720952988,
|
| 387 |
+
"eval_precision": 0.7229152342598959,
|
| 388 |
+
"eval_recall": 0.7333599043443603,
|
| 389 |
+
"eval_runtime": 37.7966,
|
| 390 |
+
"eval_samples_per_second": 79.372,
|
| 391 |
+
"eval_steps_per_second": 4.974,
|
| 392 |
+
"step": 16000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.46,
|
| 396 |
+
"learning_rate": 2.53749719542293e-05,
|
| 397 |
+
"loss": 0.0619,
|
| 398 |
+
"step": 16500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.48,
|
| 402 |
+
"learning_rate": 2.5235023558447387e-05,
|
| 403 |
+
"loss": 0.0592,
|
| 404 |
+
"step": 17000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.48,
|
| 408 |
+
"eval_accuracy": 0.979691289153627,
|
| 409 |
+
"eval_f1": 0.7246881057706644,
|
| 410 |
+
"eval_loss": 0.0674288421869278,
|
| 411 |
+
"eval_precision": 0.7229991074085094,
|
| 412 |
+
"eval_recall": 0.7263850139497808,
|
| 413 |
+
"eval_runtime": 36.2962,
|
| 414 |
+
"eval_samples_per_second": 82.653,
|
| 415 |
+
"eval_steps_per_second": 5.18,
|
| 416 |
+
"step": 17000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.49,
|
| 420 |
+
"learning_rate": 2.509479470495849e-05,
|
| 421 |
+
"loss": 0.0616,
|
| 422 |
+
"step": 17500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5,
|
| 426 |
+
"learning_rate": 2.49545658514696e-05,
|
| 427 |
+
"loss": 0.062,
|
| 428 |
+
"step": 18000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.5,
|
| 432 |
+
"eval_accuracy": 0.9812219343297894,
|
| 433 |
+
"eval_f1": 0.7340672360171793,
|
| 434 |
+
"eval_loss": 0.06332722306251526,
|
| 435 |
+
"eval_precision": 0.7274239311221994,
|
| 436 |
+
"eval_recall": 0.7408330011956955,
|
| 437 |
+
"eval_runtime": 38.753,
|
| 438 |
+
"eval_samples_per_second": 77.413,
|
| 439 |
+
"eval_steps_per_second": 4.851,
|
| 440 |
+
"step": 18000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.52,
|
| 444 |
+
"learning_rate": 2.4814336997980706e-05,
|
| 445 |
+
"loss": 0.063,
|
| 446 |
+
"step": 18500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.53,
|
| 450 |
+
"learning_rate": 2.4674108144491813e-05,
|
| 451 |
+
"loss": 0.0607,
|
| 452 |
+
"step": 19000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.53,
|
| 456 |
+
"eval_accuracy": 0.9811988824446063,
|
| 457 |
+
"eval_f1": 0.7373217115689383,
|
| 458 |
+
"eval_loss": 0.06261081993579865,
|
| 459 |
+
"eval_precision": 0.732965734541158,
|
| 460 |
+
"eval_recall": 0.7417297728178557,
|
| 461 |
+
"eval_runtime": 36.3964,
|
| 462 |
+
"eval_samples_per_second": 82.426,
|
| 463 |
+
"eval_steps_per_second": 5.165,
|
| 464 |
+
"step": 19000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.55,
|
| 468 |
+
"learning_rate": 2.4533879291002917e-05,
|
| 469 |
+
"loss": 0.0634,
|
| 470 |
+
"step": 19500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.56,
|
| 474 |
+
"learning_rate": 2.4393650437514025e-05,
|
| 475 |
+
"loss": 0.0629,
|
| 476 |
+
"step": 20000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.56,
|
| 480 |
+
"eval_accuracy": 0.9799218080054587,
|
| 481 |
+
"eval_f1": 0.7318235995232418,
|
| 482 |
+
"eval_loss": 0.07822923362255096,
|
| 483 |
+
"eval_precision": 0.7295049504950495,
|
| 484 |
+
"eval_recall": 0.7341570346751694,
|
| 485 |
+
"eval_runtime": 37.4868,
|
| 486 |
+
"eval_samples_per_second": 80.028,
|
| 487 |
+
"eval_steps_per_second": 5.015,
|
| 488 |
+
"step": 20000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.57,
|
| 492 |
+
"learning_rate": 2.425342158402513e-05,
|
| 493 |
+
"loss": 0.0613,
|
| 494 |
+
"step": 20500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.59,
|
| 498 |
+
"learning_rate": 2.4113192730536237e-05,
|
| 499 |
+
"loss": 0.0624,
|
| 500 |
+
"step": 21000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.59,
|
| 504 |
+
"eval_accuracy": 0.9803644042009756,
|
| 505 |
+
"eval_f1": 0.7339413164155432,
|
| 506 |
+
"eval_loss": 0.06663613021373749,
|
| 507 |
+
"eval_precision": 0.7301775147928994,
|
| 508 |
+
"eval_recall": 0.7377441211638103,
|
| 509 |
+
"eval_runtime": 35.995,
|
| 510 |
+
"eval_samples_per_second": 83.345,
|
| 511 |
+
"eval_steps_per_second": 5.223,
|
| 512 |
+
"step": 21000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.6,
|
| 516 |
+
"learning_rate": 2.3972963877047344e-05,
|
| 517 |
+
"loss": 0.0608,
|
| 518 |
+
"step": 21500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.62,
|
| 522 |
+
"learning_rate": 2.3833015481265426e-05,
|
| 523 |
+
"loss": 0.0624,
|
| 524 |
+
"step": 22000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.62,
|
| 528 |
+
"eval_accuracy": 0.9802122617587666,
|
| 529 |
+
"eval_f1": 0.7311229308545011,
|
| 530 |
+
"eval_loss": 0.06742220371961594,
|
| 531 |
+
"eval_precision": 0.7294911219125086,
|
| 532 |
+
"eval_recall": 0.7327620565962535,
|
| 533 |
+
"eval_runtime": 37.1663,
|
| 534 |
+
"eval_samples_per_second": 80.718,
|
| 535 |
+
"eval_steps_per_second": 5.058,
|
| 536 |
+
"step": 22000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.63,
|
| 540 |
+
"learning_rate": 2.3692786627776534e-05,
|
| 541 |
+
"loss": 0.0593,
|
| 542 |
+
"step": 22500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.65,
|
| 546 |
+
"learning_rate": 2.3552557774287638e-05,
|
| 547 |
+
"loss": 0.0593,
|
| 548 |
+
"step": 23000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.65,
|
| 552 |
+
"eval_accuracy": 0.9812634277231191,
|
| 553 |
+
"eval_f1": 0.7430700447093891,
|
| 554 |
+
"eval_loss": 0.06372907757759094,
|
| 555 |
+
"eval_precision": 0.7409352090350704,
|
| 556 |
+
"eval_recall": 0.7452172180151455,
|
| 557 |
+
"eval_runtime": 37.7419,
|
| 558 |
+
"eval_samples_per_second": 79.487,
|
| 559 |
+
"eval_steps_per_second": 4.981,
|
| 560 |
+
"step": 23000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.66,
|
| 564 |
+
"learning_rate": 2.3412328920798745e-05,
|
| 565 |
+
"loss": 0.0629,
|
| 566 |
+
"step": 23500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.67,
|
| 570 |
+
"learning_rate": 2.327210006730985e-05,
|
| 571 |
+
"loss": 0.0605,
|
| 572 |
+
"step": 24000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.67,
|
| 576 |
+
"eval_accuracy": 0.9806087541839171,
|
| 577 |
+
"eval_f1": 0.7302190657197158,
|
| 578 |
+
"eval_loss": 0.06761059165000916,
|
| 579 |
+
"eval_precision": 0.7330789315123519,
|
| 580 |
+
"eval_recall": 0.7273814268632921,
|
| 581 |
+
"eval_runtime": 37.6798,
|
| 582 |
+
"eval_samples_per_second": 79.618,
|
| 583 |
+
"eval_steps_per_second": 4.989,
|
| 584 |
+
"step": 24000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.69,
|
| 588 |
+
"learning_rate": 2.3131871213820957e-05,
|
| 589 |
+
"loss": 0.0608,
|
| 590 |
+
"step": 24500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.7,
|
| 594 |
+
"learning_rate": 2.299164236033206e-05,
|
| 595 |
+
"loss": 0.0577,
|
| 596 |
+
"step": 25000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.7,
|
| 600 |
+
"eval_accuracy": 0.9804105079713419,
|
| 601 |
+
"eval_f1": 0.7315063052328468,
|
| 602 |
+
"eval_loss": 0.07262897491455078,
|
| 603 |
+
"eval_precision": 0.7289728873936275,
|
| 604 |
+
"eval_recall": 0.7340573933838183,
|
| 605 |
+
"eval_runtime": 36.2251,
|
| 606 |
+
"eval_samples_per_second": 82.815,
|
| 607 |
+
"eval_steps_per_second": 5.19,
|
| 608 |
+
"step": 25000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.72,
|
| 612 |
+
"learning_rate": 2.285141350684317e-05,
|
| 613 |
+
"loss": 0.065,
|
| 614 |
+
"step": 25500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.73,
|
| 618 |
+
"learning_rate": 2.2711184653354273e-05,
|
| 619 |
+
"loss": 0.0616,
|
| 620 |
+
"step": 26000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.73,
|
| 624 |
+
"eval_accuracy": 0.981291089985339,
|
| 625 |
+
"eval_f1": 0.7420074349442379,
|
| 626 |
+
"eval_loss": 0.06614366918802261,
|
| 627 |
+
"eval_precision": 0.738238485057698,
|
| 628 |
+
"eval_recall": 0.7458150657632523,
|
| 629 |
+
"eval_runtime": 37.1932,
|
| 630 |
+
"eval_samples_per_second": 80.66,
|
| 631 |
+
"eval_steps_per_second": 5.055,
|
| 632 |
+
"step": 26000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.74,
|
| 636 |
+
"learning_rate": 2.257095579986538e-05,
|
| 637 |
+
"loss": 0.0587,
|
| 638 |
+
"step": 26500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.76,
|
| 642 |
+
"learning_rate": 2.2431007404083466e-05,
|
| 643 |
+
"loss": 0.0598,
|
| 644 |
+
"step": 27000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.76,
|
| 648 |
+
"eval_accuracy": 0.9814386220505112,
|
| 649 |
+
"eval_f1": 0.7464872353057589,
|
| 650 |
+
"eval_loss": 0.06462829560041428,
|
| 651 |
+
"eval_precision": 0.7413522012578616,
|
| 652 |
+
"eval_recall": 0.7516939019529693,
|
| 653 |
+
"eval_runtime": 37.4813,
|
| 654 |
+
"eval_samples_per_second": 80.04,
|
| 655 |
+
"eval_steps_per_second": 5.016,
|
| 656 |
+
"step": 27000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.77,
|
| 660 |
+
"learning_rate": 2.229077855059457e-05,
|
| 661 |
+
"loss": 0.0536,
|
| 662 |
+
"step": 27500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.79,
|
| 666 |
+
"learning_rate": 2.2150549697105678e-05,
|
| 667 |
+
"loss": 0.0596,
|
| 668 |
+
"step": 28000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.79,
|
| 672 |
+
"eval_accuracy": 0.9802906381683895,
|
| 673 |
+
"eval_f1": 0.735488974587165,
|
| 674 |
+
"eval_loss": 0.06780258566141129,
|
| 675 |
+
"eval_precision": 0.7299313052011777,
|
| 676 |
+
"eval_recall": 0.7411319250697489,
|
| 677 |
+
"eval_runtime": 37.4961,
|
| 678 |
+
"eval_samples_per_second": 80.008,
|
| 679 |
+
"eval_steps_per_second": 5.014,
|
| 680 |
+
"step": 28000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.8,
|
| 684 |
+
"learning_rate": 2.201060130132376e-05,
|
| 685 |
+
"loss": 0.0602,
|
| 686 |
+
"step": 28500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.81,
|
| 690 |
+
"learning_rate": 2.1870372447834867e-05,
|
| 691 |
+
"loss": 0.0593,
|
| 692 |
+
"step": 29000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.81,
|
| 696 |
+
"eval_accuracy": 0.9815723229845736,
|
| 697 |
+
"eval_f1": 0.7491701758731731,
|
| 698 |
+
"eval_loss": 0.06298363208770752,
|
| 699 |
+
"eval_precision": 0.7449995073406247,
|
| 700 |
+
"eval_recall": 0.7533878039059386,
|
| 701 |
+
"eval_runtime": 37.7907,
|
| 702 |
+
"eval_samples_per_second": 79.385,
|
| 703 |
+
"eval_steps_per_second": 4.975,
|
| 704 |
+
"step": 29000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.83,
|
| 708 |
+
"learning_rate": 2.173014359434597e-05,
|
| 709 |
+
"loss": 0.0586,
|
| 710 |
+
"step": 29500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.84,
|
| 714 |
+
"learning_rate": 2.158991474085708e-05,
|
| 715 |
+
"loss": 0.0619,
|
| 716 |
+
"step": 30000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.84,
|
| 720 |
+
"eval_accuracy": 0.9810697918875806,
|
| 721 |
+
"eval_f1": 0.7425102020503633,
|
| 722 |
+
"eval_loss": 0.06618673354387283,
|
| 723 |
+
"eval_precision": 0.7416981507257904,
|
| 724 |
+
"eval_recall": 0.7433240334794738,
|
| 725 |
+
"eval_runtime": 37.549,
|
| 726 |
+
"eval_samples_per_second": 79.896,
|
| 727 |
+
"eval_steps_per_second": 5.007,
|
| 728 |
+
"step": 30000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.86,
|
| 732 |
+
"learning_rate": 2.1449685887368183e-05,
|
| 733 |
+
"loss": 0.0595,
|
| 734 |
+
"step": 30500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.87,
|
| 738 |
+
"learning_rate": 2.130945703387929e-05,
|
| 739 |
+
"loss": 0.0589,
|
| 740 |
+
"step": 31000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.87,
|
| 744 |
+
"eval_accuracy": 0.9798572627269458,
|
| 745 |
+
"eval_f1": 0.7328214215396731,
|
| 746 |
+
"eval_loss": 0.06754804402589798,
|
| 747 |
+
"eval_precision": 0.724124513618677,
|
| 748 |
+
"eval_recall": 0.7417297728178557,
|
| 749 |
+
"eval_runtime": 37.8499,
|
| 750 |
+
"eval_samples_per_second": 79.261,
|
| 751 |
+
"eval_steps_per_second": 4.967,
|
| 752 |
+
"step": 31000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.88,
|
| 756 |
+
"learning_rate": 2.1169228180390395e-05,
|
| 757 |
+
"loss": 0.0593,
|
| 758 |
+
"step": 31500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.9,
|
| 762 |
+
"learning_rate": 2.1028999326901502e-05,
|
| 763 |
+
"loss": 0.0616,
|
| 764 |
+
"step": 32000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.9,
|
| 768 |
+
"eval_accuracy": 0.9811481682972033,
|
| 769 |
+
"eval_f1": 0.752437998118905,
|
| 770 |
+
"eval_loss": 0.06686053425073624,
|
| 771 |
+
"eval_precision": 0.7476635514018691,
|
| 772 |
+
"eval_recall": 0.7572738142686329,
|
| 773 |
+
"eval_runtime": 37.608,
|
| 774 |
+
"eval_samples_per_second": 79.77,
|
| 775 |
+
"eval_steps_per_second": 4.999,
|
| 776 |
+
"step": 32000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.91,
|
| 780 |
+
"learning_rate": 2.088877047341261e-05,
|
| 781 |
+
"loss": 0.0596,
|
| 782 |
+
"step": 32500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.93,
|
| 786 |
+
"learning_rate": 2.0748541619923717e-05,
|
| 787 |
+
"loss": 0.0599,
|
| 788 |
+
"step": 33000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.93,
|
| 792 |
+
"eval_accuracy": 0.9808623249209321,
|
| 793 |
+
"eval_f1": 0.7464684014869889,
|
| 794 |
+
"eval_loss": 0.0668148472905159,
|
| 795 |
+
"eval_precision": 0.7426767925830949,
|
| 796 |
+
"eval_recall": 0.7502989238740534,
|
| 797 |
+
"eval_runtime": 37.7142,
|
| 798 |
+
"eval_samples_per_second": 79.546,
|
| 799 |
+
"eval_steps_per_second": 4.985,
|
| 800 |
+
"step": 33000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.94,
|
| 804 |
+
"learning_rate": 2.06085932241418e-05,
|
| 805 |
+
"loss": 0.0611,
|
| 806 |
+
"step": 33500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.95,
|
| 810 |
+
"learning_rate": 2.0468364370652904e-05,
|
| 811 |
+
"loss": 0.0578,
|
| 812 |
+
"step": 34000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.95,
|
| 816 |
+
"eval_accuracy": 0.9800970023328508,
|
| 817 |
+
"eval_f1": 0.7286303792493615,
|
| 818 |
+
"eval_loss": 0.07239069789648056,
|
| 819 |
+
"eval_precision": 0.7186046511627907,
|
| 820 |
+
"eval_recall": 0.738939816660024,
|
| 821 |
+
"eval_runtime": 36.2678,
|
| 822 |
+
"eval_samples_per_second": 82.718,
|
| 823 |
+
"eval_steps_per_second": 5.184,
|
| 824 |
+
"step": 34000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.97,
|
| 828 |
+
"learning_rate": 2.032841597487099e-05,
|
| 829 |
+
"loss": 0.0591,
|
| 830 |
+
"step": 34500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.98,
|
| 834 |
+
"learning_rate": 2.0188187121382093e-05,
|
| 835 |
+
"loss": 0.0552,
|
| 836 |
+
"step": 35000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.98,
|
| 840 |
+
"eval_accuracy": 0.9813971286571815,
|
| 841 |
+
"eval_f1": 0.7495317890586495,
|
| 842 |
+
"eval_loss": 0.06262348592281342,
|
| 843 |
+
"eval_precision": 0.7415642676028866,
|
| 844 |
+
"eval_recall": 0.7576723794340374,
|
| 845 |
+
"eval_runtime": 37.8404,
|
| 846 |
+
"eval_samples_per_second": 79.28,
|
| 847 |
+
"eval_steps_per_second": 4.968,
|
| 848 |
+
"step": 35000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.0,
|
| 852 |
+
"learning_rate": 2.0047958267893204e-05,
|
| 853 |
+
"loss": 0.0552,
|
| 854 |
+
"step": 35500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.01,
|
| 858 |
+
"learning_rate": 1.990772941440431e-05,
|
| 859 |
+
"loss": 0.0533,
|
| 860 |
+
"step": 36000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.01,
|
| 864 |
+
"eval_accuracy": 0.981254206969046,
|
| 865 |
+
"eval_f1": 0.7463703703703705,
|
| 866 |
+
"eval_loss": 0.06460578739643097,
|
| 867 |
+
"eval_precision": 0.7398668494223615,
|
| 868 |
+
"eval_recall": 0.752989238740534,
|
| 869 |
+
"eval_runtime": 37.9225,
|
| 870 |
+
"eval_samples_per_second": 79.109,
|
| 871 |
+
"eval_steps_per_second": 4.957,
|
| 872 |
+
"step": 36000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.02,
|
| 876 |
+
"learning_rate": 1.9767500560915416e-05,
|
| 877 |
+
"loss": 0.0502,
|
| 878 |
+
"step": 36500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.04,
|
| 882 |
+
"learning_rate": 1.962727170742652e-05,
|
| 883 |
+
"loss": 0.0495,
|
| 884 |
+
"step": 37000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.04,
|
| 888 |
+
"eval_accuracy": 0.9808484937898221,
|
| 889 |
+
"eval_f1": 0.7483538789048964,
|
| 890 |
+
"eval_loss": 0.0672934502363205,
|
| 891 |
+
"eval_precision": 0.7436780478205255,
|
| 892 |
+
"eval_recall": 0.7530888800318852,
|
| 893 |
+
"eval_runtime": 37.432,
|
| 894 |
+
"eval_samples_per_second": 80.145,
|
| 895 |
+
"eval_steps_per_second": 5.022,
|
| 896 |
+
"step": 37000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.05,
|
| 900 |
+
"learning_rate": 1.9487042853937628e-05,
|
| 901 |
+
"loss": 0.051,
|
| 902 |
+
"step": 37500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.07,
|
| 906 |
+
"learning_rate": 1.9346814000448735e-05,
|
| 907 |
+
"loss": 0.0545,
|
| 908 |
+
"step": 38000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.07,
|
| 912 |
+
"eval_accuracy": 0.9808992079372251,
|
| 913 |
+
"eval_f1": 0.7423830921929782,
|
| 914 |
+
"eval_loss": 0.06774791330099106,
|
| 915 |
+
"eval_precision": 0.7358786098874205,
|
| 916 |
+
"eval_recall": 0.7490035870864886,
|
| 917 |
+
"eval_runtime": 36.4586,
|
| 918 |
+
"eval_samples_per_second": 82.285,
|
| 919 |
+
"eval_steps_per_second": 5.157,
|
| 920 |
+
"step": 38000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.08,
|
| 924 |
+
"learning_rate": 1.9206865604666817e-05,
|
| 925 |
+
"loss": 0.0517,
|
| 926 |
+
"step": 38500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.09,
|
| 930 |
+
"learning_rate": 1.9066636751177925e-05,
|
| 931 |
+
"loss": 0.0506,
|
| 932 |
+
"step": 39000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.09,
|
| 936 |
+
"eval_accuracy": 0.9809821947238845,
|
| 937 |
+
"eval_f1": 0.7475723369645586,
|
| 938 |
+
"eval_loss": 0.0674295574426651,
|
| 939 |
+
"eval_precision": 0.7397327090039996,
|
| 940 |
+
"eval_recall": 0.7555799123156636,
|
| 941 |
+
"eval_runtime": 37.4832,
|
| 942 |
+
"eval_samples_per_second": 80.036,
|
| 943 |
+
"eval_steps_per_second": 5.016,
|
| 944 |
+
"step": 39000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.11,
|
| 948 |
+
"learning_rate": 1.892640789768903e-05,
|
| 949 |
+
"loss": 0.0513,
|
| 950 |
+
"step": 39500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.12,
|
| 954 |
+
"learning_rate": 1.8786179044200137e-05,
|
| 955 |
+
"loss": 0.0505,
|
| 956 |
+
"step": 40000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 1.12,
|
| 960 |
+
"eval_accuracy": 0.9814017390342182,
|
| 961 |
+
"eval_f1": 0.7522636188214338,
|
| 962 |
+
"eval_loss": 0.06595376133918762,
|
| 963 |
+
"eval_precision": 0.7471253071253071,
|
| 964 |
+
"eval_recall": 0.7574730968513352,
|
| 965 |
+
"eval_runtime": 37.3722,
|
| 966 |
+
"eval_samples_per_second": 80.274,
|
| 967 |
+
"eval_steps_per_second": 5.03,
|
| 968 |
+
"step": 40000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.14,
|
| 972 |
+
"learning_rate": 1.864595019071124e-05,
|
| 973 |
+
"loss": 0.0497,
|
| 974 |
+
"step": 40500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.15,
|
| 978 |
+
"learning_rate": 1.8505721337222348e-05,
|
| 979 |
+
"loss": 0.0563,
|
| 980 |
+
"step": 41000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.15,
|
| 984 |
+
"eval_accuracy": 0.9808945975601885,
|
| 985 |
+
"eval_f1": 0.7516394655095903,
|
| 986 |
+
"eval_loss": 0.06491059809923172,
|
| 987 |
+
"eval_precision": 0.7439726695949244,
|
| 988 |
+
"eval_recall": 0.7594659226783579,
|
| 989 |
+
"eval_runtime": 38.0002,
|
| 990 |
+
"eval_samples_per_second": 78.947,
|
| 991 |
+
"eval_steps_per_second": 4.947,
|
| 992 |
+
"step": 41000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 1.16,
|
| 996 |
+
"learning_rate": 1.836577294144043e-05,
|
| 997 |
+
"loss": 0.0523,
|
| 998 |
+
"step": 41500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.18,
|
| 1002 |
+
"learning_rate": 1.8225544087951538e-05,
|
| 1003 |
+
"loss": 0.0502,
|
| 1004 |
+
"step": 42000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.18,
|
| 1008 |
+
"eval_accuracy": 0.9805949230528073,
|
| 1009 |
+
"eval_f1": 0.7549393414211438,
|
| 1010 |
+
"eval_loss": 0.07190626114606857,
|
| 1011 |
+
"eval_precision": 0.7503691308199626,
|
| 1012 |
+
"eval_recall": 0.7595655639697091,
|
| 1013 |
+
"eval_runtime": 37.6782,
|
| 1014 |
+
"eval_samples_per_second": 79.622,
|
| 1015 |
+
"eval_steps_per_second": 4.99,
|
| 1016 |
+
"step": 42000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.19,
|
| 1020 |
+
"learning_rate": 1.8085315234462645e-05,
|
| 1021 |
+
"loss": 0.051,
|
| 1022 |
+
"step": 42500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.21,
|
| 1026 |
+
"learning_rate": 1.794508638097375e-05,
|
| 1027 |
+
"loss": 0.0491,
|
| 1028 |
+
"step": 43000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.21,
|
| 1032 |
+
"eval_accuracy": 0.9808254419046389,
|
| 1033 |
+
"eval_f1": 0.7479091995221027,
|
| 1034 |
+
"eval_loss": 0.06869912892580032,
|
| 1035 |
+
"eval_precision": 0.7473139673696777,
|
| 1036 |
+
"eval_recall": 0.7485053806297329,
|
| 1037 |
+
"eval_runtime": 37.2482,
|
| 1038 |
+
"eval_samples_per_second": 80.541,
|
| 1039 |
+
"eval_steps_per_second": 5.047,
|
| 1040 |
+
"step": 43000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.22,
|
| 1044 |
+
"learning_rate": 1.7805137985191835e-05,
|
| 1045 |
+
"loss": 0.0497,
|
| 1046 |
+
"step": 43500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.23,
|
| 1050 |
+
"learning_rate": 1.766490913170294e-05,
|
| 1051 |
+
"loss": 0.051,
|
| 1052 |
+
"step": 44000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.23,
|
| 1056 |
+
"eval_accuracy": 0.9811850513134964,
|
| 1057 |
+
"eval_f1": 0.7476012925677354,
|
| 1058 |
+
"eval_loss": 0.0647246241569519,
|
| 1059 |
+
"eval_precision": 0.7460065482686774,
|
| 1060 |
+
"eval_recall": 0.7492028696691909,
|
| 1061 |
+
"eval_runtime": 37.6178,
|
| 1062 |
+
"eval_samples_per_second": 79.749,
|
| 1063 |
+
"eval_steps_per_second": 4.998,
|
| 1064 |
+
"step": 44000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.25,
|
| 1068 |
+
"learning_rate": 1.7524960735921025e-05,
|
| 1069 |
+
"loss": 0.0517,
|
| 1070 |
+
"step": 44500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.26,
|
| 1074 |
+
"learning_rate": 1.738473188243213e-05,
|
| 1075 |
+
"loss": 0.0495,
|
| 1076 |
+
"step": 45000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.26,
|
| 1080 |
+
"eval_accuracy": 0.9815031673290242,
|
| 1081 |
+
"eval_f1": 0.7493440269320264,
|
| 1082 |
+
"eval_loss": 0.06404220312833786,
|
| 1083 |
+
"eval_precision": 0.7446620092492374,
|
| 1084 |
+
"eval_recall": 0.7540852929453966,
|
| 1085 |
+
"eval_runtime": 37.4983,
|
| 1086 |
+
"eval_samples_per_second": 80.004,
|
| 1087 |
+
"eval_steps_per_second": 5.014,
|
| 1088 |
+
"step": 45000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.28,
|
| 1092 |
+
"learning_rate": 1.7244503028943237e-05,
|
| 1093 |
+
"loss": 0.052,
|
| 1094 |
+
"step": 45500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.29,
|
| 1098 |
+
"learning_rate": 1.710427417545434e-05,
|
| 1099 |
+
"loss": 0.0507,
|
| 1100 |
+
"step": 46000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.29,
|
| 1104 |
+
"eval_accuracy": 0.9804289494794884,
|
| 1105 |
+
"eval_f1": 0.7446007529225283,
|
| 1106 |
+
"eval_loss": 0.06634628772735596,
|
| 1107 |
+
"eval_precision": 0.7403467297084318,
|
| 1108 |
+
"eval_recall": 0.7489039457951375,
|
| 1109 |
+
"eval_runtime": 37.6634,
|
| 1110 |
+
"eval_samples_per_second": 79.653,
|
| 1111 |
+
"eval_steps_per_second": 4.992,
|
| 1112 |
+
"step": 46000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.3,
|
| 1116 |
+
"learning_rate": 1.6964045321965448e-05,
|
| 1117 |
+
"loss": 0.048,
|
| 1118 |
+
"step": 46500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.32,
|
| 1122 |
+
"learning_rate": 1.6823816468476552e-05,
|
| 1123 |
+
"loss": 0.0496,
|
| 1124 |
+
"step": 47000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.32,
|
| 1128 |
+
"eval_accuracy": 0.9806825202165033,
|
| 1129 |
+
"eval_f1": 0.7495407833986993,
|
| 1130 |
+
"eval_loss": 0.07511032372713089,
|
| 1131 |
+
"eval_precision": 0.7469080835064806,
|
| 1132 |
+
"eval_recall": 0.752192108409725,
|
| 1133 |
+
"eval_runtime": 37.4863,
|
| 1134 |
+
"eval_samples_per_second": 80.029,
|
| 1135 |
+
"eval_steps_per_second": 5.015,
|
| 1136 |
+
"step": 47000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.33,
|
| 1140 |
+
"learning_rate": 1.6683868072694638e-05,
|
| 1141 |
+
"loss": 0.0479,
|
| 1142 |
+
"step": 47500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.35,
|
| 1146 |
+
"learning_rate": 1.6543639219205746e-05,
|
| 1147 |
+
"loss": 0.0482,
|
| 1148 |
+
"step": 48000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.35,
|
| 1152 |
+
"eval_accuracy": 0.9812311550838627,
|
| 1153 |
+
"eval_f1": 0.7515115472296561,
|
| 1154 |
+
"eval_loss": 0.06654708087444305,
|
| 1155 |
+
"eval_precision": 0.7475843028988365,
|
| 1156 |
+
"eval_recall": 0.7554802710243125,
|
| 1157 |
+
"eval_runtime": 37.3402,
|
| 1158 |
+
"eval_samples_per_second": 80.342,
|
| 1159 |
+
"eval_steps_per_second": 5.035,
|
| 1160 |
+
"step": 48000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.36,
|
| 1164 |
+
"learning_rate": 1.6403690823423828e-05,
|
| 1165 |
+
"loss": 0.0496,
|
| 1166 |
+
"step": 48500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.37,
|
| 1170 |
+
"learning_rate": 1.6263461969934935e-05,
|
| 1171 |
+
"loss": 0.0499,
|
| 1172 |
+
"step": 49000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.37,
|
| 1176 |
+
"eval_accuracy": 0.9817290758038192,
|
| 1177 |
+
"eval_f1": 0.7567942181080144,
|
| 1178 |
+
"eval_loss": 0.06324990093708038,
|
| 1179 |
+
"eval_precision": 0.7519921298573536,
|
| 1180 |
+
"eval_recall": 0.7616580310880829,
|
| 1181 |
+
"eval_runtime": 37.4694,
|
| 1182 |
+
"eval_samples_per_second": 80.065,
|
| 1183 |
+
"eval_steps_per_second": 5.017,
|
| 1184 |
+
"step": 49000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.39,
|
| 1188 |
+
"learning_rate": 1.612323311644604e-05,
|
| 1189 |
+
"loss": 0.0487,
|
| 1190 |
+
"step": 49500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.4,
|
| 1194 |
+
"learning_rate": 1.5983004262957147e-05,
|
| 1195 |
+
"loss": 0.0492,
|
| 1196 |
+
"step": 50000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.4,
|
| 1200 |
+
"eval_accuracy": 0.9811158956579469,
|
| 1201 |
+
"eval_f1": 0.752822961747003,
|
| 1202 |
+
"eval_loss": 0.07030627131462097,
|
| 1203 |
+
"eval_precision": 0.7516638521903248,
|
| 1204 |
+
"eval_recall": 0.7539856516540454,
|
| 1205 |
+
"eval_runtime": 37.5303,
|
| 1206 |
+
"eval_samples_per_second": 79.935,
|
| 1207 |
+
"eval_steps_per_second": 5.009,
|
| 1208 |
+
"step": 50000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.42,
|
| 1212 |
+
"learning_rate": 1.584305586717523e-05,
|
| 1213 |
+
"loss": 0.0503,
|
| 1214 |
+
"step": 50500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.43,
|
| 1218 |
+
"learning_rate": 1.5702827013686337e-05,
|
| 1219 |
+
"loss": 0.0496,
|
| 1220 |
+
"step": 51000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.43,
|
| 1224 |
+
"eval_accuracy": 0.981719855049746,
|
| 1225 |
+
"eval_f1": 0.7585012126911844,
|
| 1226 |
+
"eval_loss": 0.06571871042251587,
|
| 1227 |
+
"eval_precision": 0.7536146355857185,
|
| 1228 |
+
"eval_recall": 0.7634515743324033,
|
| 1229 |
+
"eval_runtime": 37.9295,
|
| 1230 |
+
"eval_samples_per_second": 79.094,
|
| 1231 |
+
"eval_steps_per_second": 4.957,
|
| 1232 |
+
"step": 51000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.44,
|
| 1236 |
+
"learning_rate": 1.556259816019744e-05,
|
| 1237 |
+
"loss": 0.0477,
|
| 1238 |
+
"step": 51500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.46,
|
| 1242 |
+
"learning_rate": 1.542236930670855e-05,
|
| 1243 |
+
"loss": 0.0499,
|
| 1244 |
+
"step": 52000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.46,
|
| 1248 |
+
"eval_accuracy": 0.9822085550156292,
|
| 1249 |
+
"eval_f1": 0.7642292490118576,
|
| 1250 |
+
"eval_loss": 0.061449870467185974,
|
| 1251 |
+
"eval_precision": 0.757938063504508,
|
| 1252 |
+
"eval_recall": 0.7706257473096851,
|
| 1253 |
+
"eval_runtime": 37.5922,
|
| 1254 |
+
"eval_samples_per_second": 79.804,
|
| 1255 |
+
"eval_steps_per_second": 5.001,
|
| 1256 |
+
"step": 52000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.47,
|
| 1260 |
+
"learning_rate": 1.5282140453219652e-05,
|
| 1261 |
+
"loss": 0.0475,
|
| 1262 |
+
"step": 52500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.49,
|
| 1266 |
+
"learning_rate": 1.514191159973076e-05,
|
| 1267 |
+
"loss": 0.0475,
|
| 1268 |
+
"step": 53000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.49,
|
| 1272 |
+
"eval_accuracy": 0.9815538814764272,
|
| 1273 |
+
"eval_f1": 0.7547375191727277,
|
| 1274 |
+
"eval_loss": 0.06496689468622208,
|
| 1275 |
+
"eval_precision": 0.7495823095823095,
|
| 1276 |
+
"eval_recall": 0.7599641291351136,
|
| 1277 |
+
"eval_runtime": 37.7023,
|
| 1278 |
+
"eval_samples_per_second": 79.571,
|
| 1279 |
+
"eval_steps_per_second": 4.986,
|
| 1280 |
+
"step": 53000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.5,
|
| 1284 |
+
"learning_rate": 1.5001682746241866e-05,
|
| 1285 |
+
"loss": 0.0515,
|
| 1286 |
+
"step": 53500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 1.51,
|
| 1290 |
+
"learning_rate": 1.4861453892752973e-05,
|
| 1291 |
+
"loss": 0.048,
|
| 1292 |
+
"step": 54000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.51,
|
| 1296 |
+
"eval_accuracy": 0.9812219343297894,
|
| 1297 |
+
"eval_f1": 0.7529961708687652,
|
| 1298 |
+
"eval_loss": 0.06513578444719315,
|
| 1299 |
+
"eval_precision": 0.7516132234686786,
|
| 1300 |
+
"eval_recall": 0.75438421681945,
|
| 1301 |
+
"eval_runtime": 37.4039,
|
| 1302 |
+
"eval_samples_per_second": 80.205,
|
| 1303 |
+
"eval_steps_per_second": 5.026,
|
| 1304 |
+
"step": 54000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.53,
|
| 1308 |
+
"learning_rate": 1.4721225039264079e-05,
|
| 1309 |
+
"loss": 0.0471,
|
| 1310 |
+
"step": 54500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.54,
|
| 1314 |
+
"learning_rate": 1.4580996185775185e-05,
|
| 1315 |
+
"loss": 0.0487,
|
| 1316 |
+
"step": 55000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 1.54,
|
| 1320 |
+
"eval_accuracy": 0.9822085550156292,
|
| 1321 |
+
"eval_f1": 0.7677227722772277,
|
| 1322 |
+
"eval_loss": 0.061350539326667786,
|
| 1323 |
+
"eval_precision": 0.7628886265249901,
|
| 1324 |
+
"eval_recall": 0.7726185731367079,
|
| 1325 |
+
"eval_runtime": 37.2631,
|
| 1326 |
+
"eval_samples_per_second": 80.509,
|
| 1327 |
+
"eval_steps_per_second": 5.045,
|
| 1328 |
+
"step": 55000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.56,
|
| 1332 |
+
"learning_rate": 1.444076733228629e-05,
|
| 1333 |
+
"loss": 0.0496,
|
| 1334 |
+
"step": 55500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.57,
|
| 1338 |
+
"learning_rate": 1.4300538478797398e-05,
|
| 1339 |
+
"loss": 0.0491,
|
| 1340 |
+
"step": 56000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.57,
|
| 1344 |
+
"eval_accuracy": 0.9823653078348747,
|
| 1345 |
+
"eval_f1": 0.7622540516429598,
|
| 1346 |
+
"eval_loss": 0.06025264039635658,
|
| 1347 |
+
"eval_precision": 0.7583078591854847,
|
| 1348 |
+
"eval_recall": 0.7662415304902351,
|
| 1349 |
+
"eval_runtime": 36.0146,
|
| 1350 |
+
"eval_samples_per_second": 83.299,
|
| 1351 |
+
"eval_steps_per_second": 5.22,
|
| 1352 |
+
"step": 56000
|
| 1353 |
+
}
|
| 1354 |
+
],
|
| 1355 |
+
"max_steps": 106968,
|
| 1356 |
+
"num_train_epochs": 3,
|
| 1357 |
+
"total_flos": 3.1285620016887974e+17,
|
| 1358 |
+
"trial_name": null,
|
| 1359 |
+
"trial_params": null
|
| 1360 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac37cbfc12103f3ac2d0a67192acf08afa9f2f56f2245faab97021f7a9cb4ef1
|
| 3 |
+
size 3375
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|