Upload folder using huggingface_hub
Browse files- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +741 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base-finetuned-8M-MLM-500K-finetuned-8M-MLM-500K_Research_paper-v1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 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": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1,
|
| 23 |
+
"LABEL_2": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.37.0",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b52e9b9cf42ce9bce3b8787427abfbe8420f3f2e01226d7cf99f63ab424682e
|
| 3 |
+
size 498615900
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b02207559892ba06b1b123c3034e419c8a158f29b3c18ed5d0a498d9dc994464
|
| 3 |
+
size 997351610
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b5838433cd8dbdd7dd5243a5d968813436ace9ba74e7b3b207f2004b5680ec
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f77fd78e01f7c429953917e9436842383d0e4223de27efa904747c7c4d82eacf
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,741 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.872356495468278,
|
| 3 |
+
"best_model_checkpoint": "./Research_paper_MLM_all_CGO_Level_2_Final_Model/checkpoint-3000",
|
| 4 |
+
"epoch": 0.24,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1e-07,
|
| 14 |
+
"loss": 1.1475,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 2e-07,
|
| 20 |
+
"loss": 1.1355,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"eval_accuracy": 0.33534743202416917,
|
| 26 |
+
"eval_f1": 0.28883320685557196,
|
| 27 |
+
"eval_loss": 1.125103235244751,
|
| 28 |
+
"eval_precision": 0.25365069358986825,
|
| 29 |
+
"eval_recall": 0.33534743202416917,
|
| 30 |
+
"eval_runtime": 10.8046,
|
| 31 |
+
"eval_samples_per_second": 245.08,
|
| 32 |
+
"eval_steps_per_second": 3.887,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 1.9983974358974358e-07,
|
| 38 |
+
"loss": 1.1142,
|
| 39 |
+
"step": 150
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 1.9967948717948717e-07,
|
| 44 |
+
"loss": 1.0879,
|
| 45 |
+
"step": 200
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"eval_accuracy": 0.5143504531722054,
|
| 50 |
+
"eval_f1": 0.3499174782499206,
|
| 51 |
+
"eval_loss": 1.0747710466384888,
|
| 52 |
+
"eval_precision": 0.2651511602396808,
|
| 53 |
+
"eval_recall": 0.5143504531722054,
|
| 54 |
+
"eval_runtime": 10.7915,
|
| 55 |
+
"eval_samples_per_second": 245.378,
|
| 56 |
+
"eval_steps_per_second": 3.892,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02,
|
| 61 |
+
"learning_rate": 1.9951923076923076e-07,
|
| 62 |
+
"loss": 1.0575,
|
| 63 |
+
"step": 250
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.02,
|
| 67 |
+
"learning_rate": 1.9935897435897435e-07,
|
| 68 |
+
"loss": 1.0245,
|
| 69 |
+
"step": 300
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02,
|
| 73 |
+
"eval_accuracy": 0.5173716012084593,
|
| 74 |
+
"eval_f1": 0.3848590932649115,
|
| 75 |
+
"eval_loss": 1.0068289041519165,
|
| 76 |
+
"eval_precision": 0.5250854777959997,
|
| 77 |
+
"eval_recall": 0.5173716012084593,
|
| 78 |
+
"eval_runtime": 10.7938,
|
| 79 |
+
"eval_samples_per_second": 245.326,
|
| 80 |
+
"eval_steps_per_second": 3.891,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03,
|
| 85 |
+
"learning_rate": 1.9919871794871794e-07,
|
| 86 |
+
"loss": 0.9823,
|
| 87 |
+
"step": 350
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03,
|
| 91 |
+
"learning_rate": 1.9903846153846153e-07,
|
| 92 |
+
"loss": 0.9271,
|
| 93 |
+
"step": 400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"eval_accuracy": 0.5664652567975831,
|
| 98 |
+
"eval_f1": 0.5612424944690789,
|
| 99 |
+
"eval_loss": 0.9066060781478882,
|
| 100 |
+
"eval_precision": 0.5664412983318924,
|
| 101 |
+
"eval_recall": 0.5664652567975831,
|
| 102 |
+
"eval_runtime": 10.8011,
|
| 103 |
+
"eval_samples_per_second": 245.161,
|
| 104 |
+
"eval_steps_per_second": 3.889,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.04,
|
| 109 |
+
"learning_rate": 1.9887820512820513e-07,
|
| 110 |
+
"loss": 0.8753,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.04,
|
| 115 |
+
"learning_rate": 1.9871794871794872e-07,
|
| 116 |
+
"loss": 0.8326,
|
| 117 |
+
"step": 500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.04,
|
| 121 |
+
"eval_accuracy": 0.597809667673716,
|
| 122 |
+
"eval_f1": 0.5936208877467785,
|
| 123 |
+
"eval_loss": 0.8094537854194641,
|
| 124 |
+
"eval_precision": 0.606349562686828,
|
| 125 |
+
"eval_recall": 0.597809667673716,
|
| 126 |
+
"eval_runtime": 10.7899,
|
| 127 |
+
"eval_samples_per_second": 245.415,
|
| 128 |
+
"eval_steps_per_second": 3.893,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.04,
|
| 133 |
+
"learning_rate": 1.985576923076923e-07,
|
| 134 |
+
"loss": 0.7909,
|
| 135 |
+
"step": 550
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05,
|
| 139 |
+
"learning_rate": 1.983974358974359e-07,
|
| 140 |
+
"loss": 0.7634,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.05,
|
| 145 |
+
"eval_accuracy": 0.6185800604229608,
|
| 146 |
+
"eval_f1": 0.6127776437556779,
|
| 147 |
+
"eval_loss": 0.7459443211555481,
|
| 148 |
+
"eval_precision": 0.6315377091362361,
|
| 149 |
+
"eval_recall": 0.6185800604229608,
|
| 150 |
+
"eval_runtime": 16.0132,
|
| 151 |
+
"eval_samples_per_second": 165.364,
|
| 152 |
+
"eval_steps_per_second": 2.623,
|
| 153 |
+
"step": 600
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.05,
|
| 157 |
+
"learning_rate": 1.982371794871795e-07,
|
| 158 |
+
"loss": 0.7404,
|
| 159 |
+
"step": 650
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.06,
|
| 163 |
+
"learning_rate": 1.9807692307692308e-07,
|
| 164 |
+
"loss": 0.7334,
|
| 165 |
+
"step": 700
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.06,
|
| 169 |
+
"eval_accuracy": 0.6578549848942599,
|
| 170 |
+
"eval_f1": 0.6578987306609153,
|
| 171 |
+
"eval_loss": 0.7136017680168152,
|
| 172 |
+
"eval_precision": 0.6579792469600714,
|
| 173 |
+
"eval_recall": 0.6578549848942599,
|
| 174 |
+
"eval_runtime": 10.8054,
|
| 175 |
+
"eval_samples_per_second": 245.064,
|
| 176 |
+
"eval_steps_per_second": 3.887,
|
| 177 |
+
"step": 700
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"learning_rate": 1.9791666666666667e-07,
|
| 182 |
+
"loss": 0.7162,
|
| 183 |
+
"step": 750
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.06,
|
| 187 |
+
"learning_rate": 1.9775641025641026e-07,
|
| 188 |
+
"loss": 0.7052,
|
| 189 |
+
"step": 800
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.06,
|
| 193 |
+
"eval_accuracy": 0.68202416918429,
|
| 194 |
+
"eval_f1": 0.6820909311917643,
|
| 195 |
+
"eval_loss": 0.6918750405311584,
|
| 196 |
+
"eval_precision": 0.6825693212542151,
|
| 197 |
+
"eval_recall": 0.68202416918429,
|
| 198 |
+
"eval_runtime": 10.7979,
|
| 199 |
+
"eval_samples_per_second": 245.233,
|
| 200 |
+
"eval_steps_per_second": 3.89,
|
| 201 |
+
"step": 800
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.07,
|
| 205 |
+
"learning_rate": 1.9759615384615385e-07,
|
| 206 |
+
"loss": 0.7014,
|
| 207 |
+
"step": 850
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.07,
|
| 211 |
+
"learning_rate": 1.9743589743589744e-07,
|
| 212 |
+
"loss": 0.6917,
|
| 213 |
+
"step": 900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.07,
|
| 217 |
+
"eval_accuracy": 0.7005287009063444,
|
| 218 |
+
"eval_f1": 0.6970978787648872,
|
| 219 |
+
"eval_loss": 0.6726363897323608,
|
| 220 |
+
"eval_precision": 0.7060152626941981,
|
| 221 |
+
"eval_recall": 0.7005287009063444,
|
| 222 |
+
"eval_runtime": 10.7791,
|
| 223 |
+
"eval_samples_per_second": 245.661,
|
| 224 |
+
"eval_steps_per_second": 3.896,
|
| 225 |
+
"step": 900
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.08,
|
| 229 |
+
"learning_rate": 1.9727564102564103e-07,
|
| 230 |
+
"loss": 0.6746,
|
| 231 |
+
"step": 950
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.08,
|
| 235 |
+
"learning_rate": 1.9711538461538462e-07,
|
| 236 |
+
"loss": 0.669,
|
| 237 |
+
"step": 1000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.08,
|
| 241 |
+
"eval_accuracy": 0.722809667673716,
|
| 242 |
+
"eval_f1": 0.7197029874640588,
|
| 243 |
+
"eval_loss": 0.6518763303756714,
|
| 244 |
+
"eval_precision": 0.7290416924889942,
|
| 245 |
+
"eval_recall": 0.722809667673716,
|
| 246 |
+
"eval_runtime": 10.7984,
|
| 247 |
+
"eval_samples_per_second": 245.222,
|
| 248 |
+
"eval_steps_per_second": 3.889,
|
| 249 |
+
"step": 1000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.08,
|
| 253 |
+
"learning_rate": 1.969551282051282e-07,
|
| 254 |
+
"loss": 0.6552,
|
| 255 |
+
"step": 1050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.09,
|
| 259 |
+
"learning_rate": 1.9679487179487178e-07,
|
| 260 |
+
"loss": 0.6476,
|
| 261 |
+
"step": 1100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.09,
|
| 265 |
+
"eval_accuracy": 0.7379154078549849,
|
| 266 |
+
"eval_f1": 0.7351061135755582,
|
| 267 |
+
"eval_loss": 0.6282221674919128,
|
| 268 |
+
"eval_precision": 0.74437720980925,
|
| 269 |
+
"eval_recall": 0.7379154078549849,
|
| 270 |
+
"eval_runtime": 10.7935,
|
| 271 |
+
"eval_samples_per_second": 245.333,
|
| 272 |
+
"eval_steps_per_second": 3.891,
|
| 273 |
+
"step": 1100
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.09,
|
| 277 |
+
"learning_rate": 1.9663461538461537e-07,
|
| 278 |
+
"loss": 0.6325,
|
| 279 |
+
"step": 1150
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.1,
|
| 283 |
+
"learning_rate": 1.9647435897435896e-07,
|
| 284 |
+
"loss": 0.6252,
|
| 285 |
+
"step": 1200
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.1,
|
| 289 |
+
"eval_accuracy": 0.7492447129909365,
|
| 290 |
+
"eval_f1": 0.7452052048147401,
|
| 291 |
+
"eval_loss": 0.5985825061798096,
|
| 292 |
+
"eval_precision": 0.7607901002801604,
|
| 293 |
+
"eval_recall": 0.7492447129909365,
|
| 294 |
+
"eval_runtime": 10.8114,
|
| 295 |
+
"eval_samples_per_second": 244.926,
|
| 296 |
+
"eval_steps_per_second": 3.885,
|
| 297 |
+
"step": 1200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.1,
|
| 301 |
+
"learning_rate": 1.9631410256410255e-07,
|
| 302 |
+
"loss": 0.6067,
|
| 303 |
+
"step": 1250
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1,
|
| 307 |
+
"learning_rate": 1.9615384615384614e-07,
|
| 308 |
+
"loss": 0.5906,
|
| 309 |
+
"step": 1300
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.1,
|
| 313 |
+
"eval_accuracy": 0.7775679758308157,
|
| 314 |
+
"eval_f1": 0.7747144726300009,
|
| 315 |
+
"eval_loss": 0.5599903464317322,
|
| 316 |
+
"eval_precision": 0.7875765823937204,
|
| 317 |
+
"eval_recall": 0.7775679758308157,
|
| 318 |
+
"eval_runtime": 10.7946,
|
| 319 |
+
"eval_samples_per_second": 245.309,
|
| 320 |
+
"eval_steps_per_second": 3.891,
|
| 321 |
+
"step": 1300
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.11,
|
| 325 |
+
"learning_rate": 1.9599358974358973e-07,
|
| 326 |
+
"loss": 0.5622,
|
| 327 |
+
"step": 1350
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.11,
|
| 331 |
+
"learning_rate": 1.9583333333333332e-07,
|
| 332 |
+
"loss": 0.5391,
|
| 333 |
+
"step": 1400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.11,
|
| 337 |
+
"eval_accuracy": 0.8111782477341389,
|
| 338 |
+
"eval_f1": 0.8088711339987766,
|
| 339 |
+
"eval_loss": 0.5117343664169312,
|
| 340 |
+
"eval_precision": 0.8220985360822193,
|
| 341 |
+
"eval_recall": 0.8111782477341389,
|
| 342 |
+
"eval_runtime": 10.8029,
|
| 343 |
+
"eval_samples_per_second": 245.12,
|
| 344 |
+
"eval_steps_per_second": 3.888,
|
| 345 |
+
"step": 1400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.12,
|
| 349 |
+
"learning_rate": 1.956730769230769e-07,
|
| 350 |
+
"loss": 0.5259,
|
| 351 |
+
"step": 1450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.12,
|
| 355 |
+
"learning_rate": 1.955128205128205e-07,
|
| 356 |
+
"loss": 0.5089,
|
| 357 |
+
"step": 1500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.12,
|
| 361 |
+
"eval_accuracy": 0.8308157099697885,
|
| 362 |
+
"eval_f1": 0.8288063720795289,
|
| 363 |
+
"eval_loss": 0.46717309951782227,
|
| 364 |
+
"eval_precision": 0.8422125041602981,
|
| 365 |
+
"eval_recall": 0.8308157099697885,
|
| 366 |
+
"eval_runtime": 10.7869,
|
| 367 |
+
"eval_samples_per_second": 245.483,
|
| 368 |
+
"eval_steps_per_second": 3.894,
|
| 369 |
+
"step": 1500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.12,
|
| 373 |
+
"learning_rate": 1.953525641025641e-07,
|
| 374 |
+
"loss": 0.4812,
|
| 375 |
+
"step": 1550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.13,
|
| 379 |
+
"learning_rate": 1.9519230769230768e-07,
|
| 380 |
+
"loss": 0.4581,
|
| 381 |
+
"step": 1600
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.13,
|
| 385 |
+
"eval_accuracy": 0.8466767371601208,
|
| 386 |
+
"eval_f1": 0.8452935464575092,
|
| 387 |
+
"eval_loss": 0.42611148953437805,
|
| 388 |
+
"eval_precision": 0.8553191629170025,
|
| 389 |
+
"eval_recall": 0.8466767371601208,
|
| 390 |
+
"eval_runtime": 10.811,
|
| 391 |
+
"eval_samples_per_second": 244.936,
|
| 392 |
+
"eval_steps_per_second": 3.885,
|
| 393 |
+
"step": 1600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.13,
|
| 397 |
+
"learning_rate": 1.9503205128205127e-07,
|
| 398 |
+
"loss": 0.4265,
|
| 399 |
+
"step": 1650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.14,
|
| 403 |
+
"learning_rate": 1.9487179487179486e-07,
|
| 404 |
+
"loss": 0.4174,
|
| 405 |
+
"step": 1700
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.14,
|
| 409 |
+
"eval_accuracy": 0.8591389728096677,
|
| 410 |
+
"eval_f1": 0.8581333993450322,
|
| 411 |
+
"eval_loss": 0.3975095748901367,
|
| 412 |
+
"eval_precision": 0.865914594919593,
|
| 413 |
+
"eval_recall": 0.8591389728096677,
|
| 414 |
+
"eval_runtime": 15.8476,
|
| 415 |
+
"eval_samples_per_second": 167.092,
|
| 416 |
+
"eval_steps_per_second": 2.65,
|
| 417 |
+
"step": 1700
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.14,
|
| 421 |
+
"learning_rate": 1.9471153846153845e-07,
|
| 422 |
+
"loss": 0.3979,
|
| 423 |
+
"step": 1750
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.14,
|
| 427 |
+
"learning_rate": 1.9455128205128204e-07,
|
| 428 |
+
"loss": 0.3897,
|
| 429 |
+
"step": 1800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.14,
|
| 433 |
+
"eval_accuracy": 0.8557401812688822,
|
| 434 |
+
"eval_f1": 0.854075463670531,
|
| 435 |
+
"eval_loss": 0.3941803574562073,
|
| 436 |
+
"eval_precision": 0.8677897892001838,
|
| 437 |
+
"eval_recall": 0.8557401812688822,
|
| 438 |
+
"eval_runtime": 10.7957,
|
| 439 |
+
"eval_samples_per_second": 245.283,
|
| 440 |
+
"eval_steps_per_second": 3.89,
|
| 441 |
+
"step": 1800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.15,
|
| 445 |
+
"learning_rate": 1.9439102564102564e-07,
|
| 446 |
+
"loss": 0.3619,
|
| 447 |
+
"step": 1850
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.15,
|
| 451 |
+
"learning_rate": 1.9423076923076923e-07,
|
| 452 |
+
"loss": 0.3511,
|
| 453 |
+
"step": 1900
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.15,
|
| 457 |
+
"eval_accuracy": 0.8576283987915407,
|
| 458 |
+
"eval_f1": 0.8557767441533479,
|
| 459 |
+
"eval_loss": 0.3930197060108185,
|
| 460 |
+
"eval_precision": 0.8716354305639,
|
| 461 |
+
"eval_recall": 0.8576283987915407,
|
| 462 |
+
"eval_runtime": 10.8129,
|
| 463 |
+
"eval_samples_per_second": 244.893,
|
| 464 |
+
"eval_steps_per_second": 3.884,
|
| 465 |
+
"step": 1900
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.16,
|
| 469 |
+
"learning_rate": 1.9407051282051282e-07,
|
| 470 |
+
"loss": 0.3537,
|
| 471 |
+
"step": 1950
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.16,
|
| 475 |
+
"learning_rate": 1.939102564102564e-07,
|
| 476 |
+
"loss": 0.3466,
|
| 477 |
+
"step": 2000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.16,
|
| 481 |
+
"eval_accuracy": 0.8606495468277946,
|
| 482 |
+
"eval_f1": 0.8590762411480044,
|
| 483 |
+
"eval_loss": 0.3839268088340759,
|
| 484 |
+
"eval_precision": 0.8725861729431068,
|
| 485 |
+
"eval_recall": 0.8606495468277946,
|
| 486 |
+
"eval_runtime": 10.8113,
|
| 487 |
+
"eval_samples_per_second": 244.93,
|
| 488 |
+
"eval_steps_per_second": 3.885,
|
| 489 |
+
"step": 2000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.16,
|
| 493 |
+
"learning_rate": 1.9375e-07,
|
| 494 |
+
"loss": 0.3521,
|
| 495 |
+
"step": 2050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.17,
|
| 499 |
+
"learning_rate": 1.935897435897436e-07,
|
| 500 |
+
"loss": 0.3389,
|
| 501 |
+
"step": 2100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.17,
|
| 505 |
+
"eval_accuracy": 0.8606495468277946,
|
| 506 |
+
"eval_f1": 0.8588371845957175,
|
| 507 |
+
"eval_loss": 0.39029455184936523,
|
| 508 |
+
"eval_precision": 0.8748009772925901,
|
| 509 |
+
"eval_recall": 0.8606495468277946,
|
| 510 |
+
"eval_runtime": 10.802,
|
| 511 |
+
"eval_samples_per_second": 245.14,
|
| 512 |
+
"eval_steps_per_second": 3.888,
|
| 513 |
+
"step": 2100
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.17,
|
| 517 |
+
"learning_rate": 1.9342948717948718e-07,
|
| 518 |
+
"loss": 0.3238,
|
| 519 |
+
"step": 2150
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.18,
|
| 523 |
+
"learning_rate": 1.9326923076923077e-07,
|
| 524 |
+
"loss": 0.3075,
|
| 525 |
+
"step": 2200
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.18,
|
| 529 |
+
"eval_accuracy": 0.8602719033232629,
|
| 530 |
+
"eval_f1": 0.8583410955489438,
|
| 531 |
+
"eval_loss": 0.3917655050754547,
|
| 532 |
+
"eval_precision": 0.8754701190846773,
|
| 533 |
+
"eval_recall": 0.8602719033232629,
|
| 534 |
+
"eval_runtime": 10.8054,
|
| 535 |
+
"eval_samples_per_second": 245.064,
|
| 536 |
+
"eval_steps_per_second": 3.887,
|
| 537 |
+
"step": 2200
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.18,
|
| 541 |
+
"learning_rate": 1.9310897435897436e-07,
|
| 542 |
+
"loss": 0.3102,
|
| 543 |
+
"step": 2250
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.18,
|
| 547 |
+
"learning_rate": 1.9294871794871795e-07,
|
| 548 |
+
"loss": 0.3101,
|
| 549 |
+
"step": 2300
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.18,
|
| 553 |
+
"eval_accuracy": 0.8666918429003021,
|
| 554 |
+
"eval_f1": 0.8652087190619578,
|
| 555 |
+
"eval_loss": 0.3828712999820709,
|
| 556 |
+
"eval_precision": 0.878661956862829,
|
| 557 |
+
"eval_recall": 0.8666918429003021,
|
| 558 |
+
"eval_runtime": 15.99,
|
| 559 |
+
"eval_samples_per_second": 165.604,
|
| 560 |
+
"eval_steps_per_second": 2.627,
|
| 561 |
+
"step": 2300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.19,
|
| 565 |
+
"learning_rate": 1.9278846153846154e-07,
|
| 566 |
+
"loss": 0.2863,
|
| 567 |
+
"step": 2350
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.19,
|
| 571 |
+
"learning_rate": 1.9262820512820513e-07,
|
| 572 |
+
"loss": 0.3009,
|
| 573 |
+
"step": 2400
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.19,
|
| 577 |
+
"eval_accuracy": 0.8621601208459214,
|
| 578 |
+
"eval_f1": 0.8602680217103188,
|
| 579 |
+
"eval_loss": 0.4013417959213257,
|
| 580 |
+
"eval_precision": 0.8773335989772154,
|
| 581 |
+
"eval_recall": 0.8621601208459214,
|
| 582 |
+
"eval_runtime": 10.8074,
|
| 583 |
+
"eval_samples_per_second": 245.018,
|
| 584 |
+
"eval_steps_per_second": 3.886,
|
| 585 |
+
"step": 2400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2,
|
| 589 |
+
"learning_rate": 1.9246794871794872e-07,
|
| 590 |
+
"loss": 0.306,
|
| 591 |
+
"step": 2450
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.2,
|
| 595 |
+
"learning_rate": 1.9230769230769231e-07,
|
| 596 |
+
"loss": 0.2866,
|
| 597 |
+
"step": 2500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.2,
|
| 601 |
+
"eval_accuracy": 0.8640483383685801,
|
| 602 |
+
"eval_f1": 0.862268075795537,
|
| 603 |
+
"eval_loss": 0.3997219502925873,
|
| 604 |
+
"eval_precision": 0.8784797318905917,
|
| 605 |
+
"eval_recall": 0.8640483383685801,
|
| 606 |
+
"eval_runtime": 10.796,
|
| 607 |
+
"eval_samples_per_second": 245.277,
|
| 608 |
+
"eval_steps_per_second": 3.89,
|
| 609 |
+
"step": 2500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.2,
|
| 613 |
+
"learning_rate": 1.921474358974359e-07,
|
| 614 |
+
"loss": 0.2747,
|
| 615 |
+
"step": 2550
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.21,
|
| 619 |
+
"learning_rate": 1.919871794871795e-07,
|
| 620 |
+
"loss": 0.2856,
|
| 621 |
+
"step": 2600
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.21,
|
| 625 |
+
"eval_accuracy": 0.8587613293051359,
|
| 626 |
+
"eval_f1": 0.8564860641576998,
|
| 627 |
+
"eval_loss": 0.4260440468788147,
|
| 628 |
+
"eval_precision": 0.8769254342874869,
|
| 629 |
+
"eval_recall": 0.8587613293051359,
|
| 630 |
+
"eval_runtime": 10.798,
|
| 631 |
+
"eval_samples_per_second": 245.231,
|
| 632 |
+
"eval_steps_per_second": 3.89,
|
| 633 |
+
"step": 2600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.21,
|
| 637 |
+
"learning_rate": 1.9182692307692309e-07,
|
| 638 |
+
"loss": 0.2907,
|
| 639 |
+
"step": 2650
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.22,
|
| 643 |
+
"learning_rate": 1.9166666666666668e-07,
|
| 644 |
+
"loss": 0.2871,
|
| 645 |
+
"step": 2700
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.22,
|
| 649 |
+
"eval_accuracy": 0.8632930513595166,
|
| 650 |
+
"eval_f1": 0.8613280138625302,
|
| 651 |
+
"eval_loss": 0.4157187342643738,
|
| 652 |
+
"eval_precision": 0.8793867110640158,
|
| 653 |
+
"eval_recall": 0.8632930513595166,
|
| 654 |
+
"eval_runtime": 10.8079,
|
| 655 |
+
"eval_samples_per_second": 245.007,
|
| 656 |
+
"eval_steps_per_second": 3.886,
|
| 657 |
+
"step": 2700
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.22,
|
| 661 |
+
"learning_rate": 1.9150641025641027e-07,
|
| 662 |
+
"loss": 0.2585,
|
| 663 |
+
"step": 2750
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.22,
|
| 667 |
+
"learning_rate": 1.9134615384615386e-07,
|
| 668 |
+
"loss": 0.2894,
|
| 669 |
+
"step": 2800
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.22,
|
| 673 |
+
"eval_accuracy": 0.8644259818731118,
|
| 674 |
+
"eval_f1": 0.8624898933835367,
|
| 675 |
+
"eval_loss": 0.4176577627658844,
|
| 676 |
+
"eval_precision": 0.8804547245205405,
|
| 677 |
+
"eval_recall": 0.8644259818731118,
|
| 678 |
+
"eval_runtime": 10.8056,
|
| 679 |
+
"eval_samples_per_second": 245.059,
|
| 680 |
+
"eval_steps_per_second": 3.887,
|
| 681 |
+
"step": 2800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.23,
|
| 685 |
+
"learning_rate": 1.9118589743589745e-07,
|
| 686 |
+
"loss": 0.2551,
|
| 687 |
+
"step": 2850
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.23,
|
| 691 |
+
"learning_rate": 1.9102564102564104e-07,
|
| 692 |
+
"loss": 0.2755,
|
| 693 |
+
"step": 2900
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.23,
|
| 697 |
+
"eval_accuracy": 0.8659365558912386,
|
| 698 |
+
"eval_f1": 0.8639206748641556,
|
| 699 |
+
"eval_loss": 0.4247892498970032,
|
| 700 |
+
"eval_precision": 0.8830682801454843,
|
| 701 |
+
"eval_recall": 0.8659365558912386,
|
| 702 |
+
"eval_runtime": 10.8115,
|
| 703 |
+
"eval_samples_per_second": 244.924,
|
| 704 |
+
"eval_steps_per_second": 3.885,
|
| 705 |
+
"step": 2900
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.24,
|
| 709 |
+
"learning_rate": 1.9086538461538463e-07,
|
| 710 |
+
"loss": 0.2494,
|
| 711 |
+
"step": 2950
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.24,
|
| 715 |
+
"learning_rate": 1.9070512820512822e-07,
|
| 716 |
+
"loss": 0.2508,
|
| 717 |
+
"step": 3000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.24,
|
| 721 |
+
"eval_accuracy": 0.872356495468278,
|
| 722 |
+
"eval_f1": 0.8707077161534905,
|
| 723 |
+
"eval_loss": 0.41548070311546326,
|
| 724 |
+
"eval_precision": 0.8869475341602814,
|
| 725 |
+
"eval_recall": 0.872356495468278,
|
| 726 |
+
"eval_runtime": 10.7909,
|
| 727 |
+
"eval_samples_per_second": 245.393,
|
| 728 |
+
"eval_steps_per_second": 3.892,
|
| 729 |
+
"step": 3000
|
| 730 |
+
}
|
| 731 |
+
],
|
| 732 |
+
"logging_steps": 50,
|
| 733 |
+
"max_steps": 62500,
|
| 734 |
+
"num_input_tokens_seen": 0,
|
| 735 |
+
"num_train_epochs": 5,
|
| 736 |
+
"save_steps": 100,
|
| 737 |
+
"total_flos": 2.5209554336064e+16,
|
| 738 |
+
"train_batch_size": 32,
|
| 739 |
+
"trial_name": null,
|
| 740 |
+
"trial_params": null
|
| 741 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55cbbc9dc2583f7316483340f7e71af41ca78ac221f5923fdc114bcc6e11c329
|
| 3 |
+
size 4664
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|