Upload folder using huggingface_hub
Browse files- checkpoint-5300/config.json +72 -0
- checkpoint-5300/model.safetensors +3 -0
- checkpoint-5300/optimizer.pt +3 -0
- checkpoint-5300/rng_state.pth +3 -0
- checkpoint-5300/scheduler.pt +3 -0
- checkpoint-5300/special_tokens_map.json +7 -0
- checkpoint-5300/tokenizer.json +0 -0
- checkpoint-5300/tokenizer_config.json +59 -0
- checkpoint-5300/trainer_state.json +1200 -0
- checkpoint-5300/training_args.bin +3 -0
- checkpoint-5300/vocab.txt +0 -0
- checkpoint-8236/config.json +72 -0
- checkpoint-8236/model.safetensors +3 -0
- checkpoint-8236/optimizer.pt +3 -0
- checkpoint-8236/rng_state.pth +3 -0
- checkpoint-8236/scheduler.pt +3 -0
- checkpoint-8236/special_tokens_map.json +7 -0
- checkpoint-8236/tokenizer.json +0 -0
- checkpoint-8236/tokenizer_config.json +59 -0
- checkpoint-8236/trainer_state.json +1838 -0
- checkpoint-8236/training_args.bin +3 -0
- checkpoint-8236/vocab.txt +0 -0
- config.json +72 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-5300/config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_10": 10,
|
| 40 |
+
"LABEL_11": 11,
|
| 41 |
+
"LABEL_12": 12,
|
| 42 |
+
"LABEL_13": 13,
|
| 43 |
+
"LABEL_14": 14,
|
| 44 |
+
"LABEL_15": 15,
|
| 45 |
+
"LABEL_16": 16,
|
| 46 |
+
"LABEL_17": 17,
|
| 47 |
+
"LABEL_18": 18,
|
| 48 |
+
"LABEL_19": 19,
|
| 49 |
+
"LABEL_2": 2,
|
| 50 |
+
"LABEL_20": 20,
|
| 51 |
+
"LABEL_3": 3,
|
| 52 |
+
"LABEL_4": 4,
|
| 53 |
+
"LABEL_5": 5,
|
| 54 |
+
"LABEL_6": 6,
|
| 55 |
+
"LABEL_7": 7,
|
| 56 |
+
"LABEL_8": 8,
|
| 57 |
+
"LABEL_9": 9
|
| 58 |
+
},
|
| 59 |
+
"layer_norm_eps": 1e-12,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"model_type": "bert",
|
| 62 |
+
"num_attention_heads": 12,
|
| 63 |
+
"num_hidden_layers": 12,
|
| 64 |
+
"pad_token_id": 0,
|
| 65 |
+
"position_embedding_type": "absolute",
|
| 66 |
+
"problem_type": "single_label_classification",
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.52.4",
|
| 69 |
+
"type_vocab_size": 2,
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 30000
|
| 72 |
+
}
|
checkpoint-5300/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6377d16c4d7efc62c1157e3da9237b2bcab325b3b1ce7725332f9ccbd626f5c
|
| 3 |
+
size 436413500
|
checkpoint-5300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac2e6bc9c1e711d50aad91763587d21cd3a5ef6859302ae461526da00eeedefc
|
| 3 |
+
size 872948026
|
checkpoint-5300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba3a8d68cd156cd4eb27a2254311fe890b3d32bafe40d2c741fc8048e4307e15
|
| 3 |
+
size 14244
|
checkpoint-5300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97d7a9ee52eed7d00a46db4d002426ed6022b68cea12f4176874e7b2ef89a356
|
| 3 |
+
size 1064
|
checkpoint-5300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-5300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-5300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-5300/trainer_state.json
ADDED
|
@@ -0,0 +1,1200 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 5300,
|
| 3 |
+
"best_metric": 0.846949212010463,
|
| 4 |
+
"best_model_checkpoint": "./camelbert-ner-author/checkpoint-5300",
|
| 5 |
+
"epoch": 2.5740650801359886,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 5300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04856726566294318,
|
| 14 |
+
"grad_norm": 13.77788257598877,
|
| 15 |
+
"learning_rate": 1.9759592034968435e-05,
|
| 16 |
+
"loss": 2.5655,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04856726566294318,
|
| 21 |
+
"eval_accuracy": 0.4197738753909069,
|
| 22 |
+
"eval_f1_macro": 0.3205328980120634,
|
| 23 |
+
"eval_f1_micro": 0.4197738753909069,
|
| 24 |
+
"eval_loss": 2.164029121398926,
|
| 25 |
+
"eval_precision_macro": 0.42432855880852344,
|
| 26 |
+
"eval_precision_micro": 0.4197738753909069,
|
| 27 |
+
"eval_recall_macro": 0.39236584110181216,
|
| 28 |
+
"eval_recall_micro": 0.4197738753909069,
|
| 29 |
+
"eval_runtime": 77.4428,
|
| 30 |
+
"eval_samples_per_second": 53.678,
|
| 31 |
+
"eval_steps_per_second": 3.357,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09713453132588636,
|
| 36 |
+
"grad_norm": 11.284036636352539,
|
| 37 |
+
"learning_rate": 1.9516755706653716e-05,
|
| 38 |
+
"loss": 1.7809,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.09713453132588636,
|
| 43 |
+
"eval_accuracy": 0.5876834255472697,
|
| 44 |
+
"eval_f1_macro": 0.5021998875928434,
|
| 45 |
+
"eval_f1_micro": 0.5876834255472697,
|
| 46 |
+
"eval_loss": 1.547103762626648,
|
| 47 |
+
"eval_precision_macro": 0.5640550767871323,
|
| 48 |
+
"eval_precision_micro": 0.5876834255472697,
|
| 49 |
+
"eval_recall_macro": 0.5447230363092859,
|
| 50 |
+
"eval_recall_micro": 0.5876834255472697,
|
| 51 |
+
"eval_runtime": 77.3875,
|
| 52 |
+
"eval_samples_per_second": 53.717,
|
| 53 |
+
"eval_steps_per_second": 3.36,
|
| 54 |
+
"step": 200
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.14570179698882954,
|
| 58 |
+
"grad_norm": 15.53082275390625,
|
| 59 |
+
"learning_rate": 1.9273919378339e-05,
|
| 60 |
+
"loss": 1.2903,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.14570179698882954,
|
| 65 |
+
"eval_accuracy": 0.6300216502285302,
|
| 66 |
+
"eval_f1_macro": 0.5639062324413268,
|
| 67 |
+
"eval_f1_micro": 0.6300216502285302,
|
| 68 |
+
"eval_loss": 1.3453640937805176,
|
| 69 |
+
"eval_precision_macro": 0.5883696452747289,
|
| 70 |
+
"eval_precision_micro": 0.6300216502285302,
|
| 71 |
+
"eval_recall_macro": 0.6245065052027649,
|
| 72 |
+
"eval_recall_micro": 0.6300216502285302,
|
| 73 |
+
"eval_runtime": 77.7169,
|
| 74 |
+
"eval_samples_per_second": 53.489,
|
| 75 |
+
"eval_steps_per_second": 3.345,
|
| 76 |
+
"step": 300
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.1942690626517727,
|
| 80 |
+
"grad_norm": 12.855542182922363,
|
| 81 |
+
"learning_rate": 1.9031083050024287e-05,
|
| 82 |
+
"loss": 1.0303,
|
| 83 |
+
"step": 400
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.1942690626517727,
|
| 87 |
+
"eval_accuracy": 0.6980995910512389,
|
| 88 |
+
"eval_f1_macro": 0.621757249063289,
|
| 89 |
+
"eval_f1_micro": 0.6980995910512389,
|
| 90 |
+
"eval_loss": 1.0540422201156616,
|
| 91 |
+
"eval_precision_macro": 0.6363865097952114,
|
| 92 |
+
"eval_precision_micro": 0.6980995910512389,
|
| 93 |
+
"eval_recall_macro": 0.6615766427269236,
|
| 94 |
+
"eval_recall_micro": 0.6980995910512389,
|
| 95 |
+
"eval_runtime": 78.209,
|
| 96 |
+
"eval_samples_per_second": 53.152,
|
| 97 |
+
"eval_steps_per_second": 3.324,
|
| 98 |
+
"step": 400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.24283632831471588,
|
| 102 |
+
"grad_norm": 13.974908828735352,
|
| 103 |
+
"learning_rate": 1.8788246721709567e-05,
|
| 104 |
+
"loss": 0.7461,
|
| 105 |
+
"step": 500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.24283632831471588,
|
| 109 |
+
"eval_accuracy": 0.697618474861679,
|
| 110 |
+
"eval_f1_macro": 0.6189270686060082,
|
| 111 |
+
"eval_f1_micro": 0.697618474861679,
|
| 112 |
+
"eval_loss": 1.0767923593521118,
|
| 113 |
+
"eval_precision_macro": 0.6453274802012455,
|
| 114 |
+
"eval_precision_micro": 0.697618474861679,
|
| 115 |
+
"eval_recall_macro": 0.6631935550298835,
|
| 116 |
+
"eval_recall_micro": 0.697618474861679,
|
| 117 |
+
"eval_runtime": 77.7991,
|
| 118 |
+
"eval_samples_per_second": 53.433,
|
| 119 |
+
"eval_steps_per_second": 3.342,
|
| 120 |
+
"step": 500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.2914035939776591,
|
| 124 |
+
"grad_norm": 15.981602668762207,
|
| 125 |
+
"learning_rate": 1.8545410393394855e-05,
|
| 126 |
+
"loss": 0.7715,
|
| 127 |
+
"step": 600
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.2914035939776591,
|
| 131 |
+
"eval_accuracy": 0.6793360596584075,
|
| 132 |
+
"eval_f1_macro": 0.6412879956515993,
|
| 133 |
+
"eval_f1_micro": 0.6793360596584075,
|
| 134 |
+
"eval_loss": 1.0772430896759033,
|
| 135 |
+
"eval_precision_macro": 0.6604751299557832,
|
| 136 |
+
"eval_precision_micro": 0.6793360596584075,
|
| 137 |
+
"eval_recall_macro": 0.6882200466749144,
|
| 138 |
+
"eval_recall_micro": 0.6793360596584075,
|
| 139 |
+
"eval_runtime": 78.3813,
|
| 140 |
+
"eval_samples_per_second": 53.036,
|
| 141 |
+
"eval_steps_per_second": 3.317,
|
| 142 |
+
"step": 600
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.33997085964060225,
|
| 146 |
+
"grad_norm": 15.210453033447266,
|
| 147 |
+
"learning_rate": 1.8302574065080135e-05,
|
| 148 |
+
"loss": 0.5764,
|
| 149 |
+
"step": 700
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.33997085964060225,
|
| 153 |
+
"eval_accuracy": 0.7346644214577821,
|
| 154 |
+
"eval_f1_macro": 0.6644040766448638,
|
| 155 |
+
"eval_f1_micro": 0.7346644214577821,
|
| 156 |
+
"eval_loss": 0.9163544178009033,
|
| 157 |
+
"eval_precision_macro": 0.6814907504685033,
|
| 158 |
+
"eval_precision_micro": 0.7346644214577821,
|
| 159 |
+
"eval_recall_macro": 0.7012321944408646,
|
| 160 |
+
"eval_recall_micro": 0.7346644214577821,
|
| 161 |
+
"eval_runtime": 77.9074,
|
| 162 |
+
"eval_samples_per_second": 53.358,
|
| 163 |
+
"eval_steps_per_second": 3.337,
|
| 164 |
+
"step": 700
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3885381253035454,
|
| 168 |
+
"grad_norm": 33.91225051879883,
|
| 169 |
+
"learning_rate": 1.8059737736765423e-05,
|
| 170 |
+
"loss": 0.5638,
|
| 171 |
+
"step": 800
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.3885381253035454,
|
| 175 |
+
"eval_accuracy": 0.7474140004811162,
|
| 176 |
+
"eval_f1_macro": 0.6913277390868877,
|
| 177 |
+
"eval_f1_micro": 0.7474140004811162,
|
| 178 |
+
"eval_loss": 0.889366090297699,
|
| 179 |
+
"eval_precision_macro": 0.7266313115490612,
|
| 180 |
+
"eval_precision_micro": 0.7474140004811162,
|
| 181 |
+
"eval_recall_macro": 0.715908295360388,
|
| 182 |
+
"eval_recall_micro": 0.7474140004811162,
|
| 183 |
+
"eval_runtime": 78.3481,
|
| 184 |
+
"eval_samples_per_second": 53.058,
|
| 185 |
+
"eval_steps_per_second": 3.319,
|
| 186 |
+
"step": 800
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4371053909664886,
|
| 190 |
+
"grad_norm": 8.672567367553711,
|
| 191 |
+
"learning_rate": 1.7816901408450707e-05,
|
| 192 |
+
"loss": 0.5197,
|
| 193 |
+
"step": 900
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.4371053909664886,
|
| 197 |
+
"eval_accuracy": 0.7926389222997354,
|
| 198 |
+
"eval_f1_macro": 0.7247243935175413,
|
| 199 |
+
"eval_f1_micro": 0.7926389222997354,
|
| 200 |
+
"eval_loss": 0.7225074768066406,
|
| 201 |
+
"eval_precision_macro": 0.7255052815535598,
|
| 202 |
+
"eval_precision_micro": 0.7926389222997354,
|
| 203 |
+
"eval_recall_macro": 0.7576197995601733,
|
| 204 |
+
"eval_recall_micro": 0.7926389222997354,
|
| 205 |
+
"eval_runtime": 78.3587,
|
| 206 |
+
"eval_samples_per_second": 53.051,
|
| 207 |
+
"eval_steps_per_second": 3.318,
|
| 208 |
+
"step": 900
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.48567265662943176,
|
| 212 |
+
"grad_norm": 5.37787389755249,
|
| 213 |
+
"learning_rate": 1.757406508013599e-05,
|
| 214 |
+
"loss": 0.4454,
|
| 215 |
+
"step": 1000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.48567265662943176,
|
| 219 |
+
"eval_accuracy": 0.7611258118835699,
|
| 220 |
+
"eval_f1_macro": 0.6918902246005824,
|
| 221 |
+
"eval_f1_micro": 0.7611258118835699,
|
| 222 |
+
"eval_loss": 0.8200820684432983,
|
| 223 |
+
"eval_precision_macro": 0.7248507826718404,
|
| 224 |
+
"eval_precision_micro": 0.7611258118835699,
|
| 225 |
+
"eval_recall_macro": 0.7240661179940105,
|
| 226 |
+
"eval_recall_micro": 0.7611258118835699,
|
| 227 |
+
"eval_runtime": 77.9125,
|
| 228 |
+
"eval_samples_per_second": 53.355,
|
| 229 |
+
"eval_steps_per_second": 3.337,
|
| 230 |
+
"step": 1000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.5342399222923749,
|
| 234 |
+
"grad_norm": 50.15217971801758,
|
| 235 |
+
"learning_rate": 1.7331228751821275e-05,
|
| 236 |
+
"loss": 0.3573,
|
| 237 |
+
"step": 1100
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.5342399222923749,
|
| 241 |
+
"eval_accuracy": 0.7486167909550157,
|
| 242 |
+
"eval_f1_macro": 0.708488926204985,
|
| 243 |
+
"eval_f1_micro": 0.7486167909550158,
|
| 244 |
+
"eval_loss": 0.840596616268158,
|
| 245 |
+
"eval_precision_macro": 0.7458516807418488,
|
| 246 |
+
"eval_precision_micro": 0.7486167909550157,
|
| 247 |
+
"eval_recall_macro": 0.7355897302661839,
|
| 248 |
+
"eval_recall_micro": 0.7486167909550157,
|
| 249 |
+
"eval_runtime": 77.9539,
|
| 250 |
+
"eval_samples_per_second": 53.326,
|
| 251 |
+
"eval_steps_per_second": 3.335,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.5828071879553182,
|
| 256 |
+
"grad_norm": 4.126067161560059,
|
| 257 |
+
"learning_rate": 1.708839242350656e-05,
|
| 258 |
+
"loss": 0.3992,
|
| 259 |
+
"step": 1200
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.5828071879553182,
|
| 263 |
+
"eval_accuracy": 0.7969689680057734,
|
| 264 |
+
"eval_f1_macro": 0.7545628662653078,
|
| 265 |
+
"eval_f1_micro": 0.7969689680057734,
|
| 266 |
+
"eval_loss": 0.7257721424102783,
|
| 267 |
+
"eval_precision_macro": 0.7815422636293521,
|
| 268 |
+
"eval_precision_micro": 0.7969689680057734,
|
| 269 |
+
"eval_recall_macro": 0.76812907504405,
|
| 270 |
+
"eval_recall_micro": 0.7969689680057734,
|
| 271 |
+
"eval_runtime": 78.4205,
|
| 272 |
+
"eval_samples_per_second": 53.009,
|
| 273 |
+
"eval_steps_per_second": 3.315,
|
| 274 |
+
"step": 1200
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.6313744536182613,
|
| 278 |
+
"grad_norm": 9.667169570922852,
|
| 279 |
+
"learning_rate": 1.6845556095191843e-05,
|
| 280 |
+
"loss": 0.3637,
|
| 281 |
+
"step": 1300
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.6313744536182613,
|
| 285 |
+
"eval_accuracy": 0.8181380803464037,
|
| 286 |
+
"eval_f1_macro": 0.7552426483349393,
|
| 287 |
+
"eval_f1_micro": 0.8181380803464037,
|
| 288 |
+
"eval_loss": 0.6487129330635071,
|
| 289 |
+
"eval_precision_macro": 0.770444338655661,
|
| 290 |
+
"eval_precision_micro": 0.8181380803464037,
|
| 291 |
+
"eval_recall_macro": 0.7814605757463501,
|
| 292 |
+
"eval_recall_micro": 0.8181380803464037,
|
| 293 |
+
"eval_runtime": 77.6598,
|
| 294 |
+
"eval_samples_per_second": 53.528,
|
| 295 |
+
"eval_steps_per_second": 3.348,
|
| 296 |
+
"step": 1300
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6799417192812045,
|
| 300 |
+
"grad_norm": 15.598691940307617,
|
| 301 |
+
"learning_rate": 1.6602719766877127e-05,
|
| 302 |
+
"loss": 0.3534,
|
| 303 |
+
"step": 1400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6799417192812045,
|
| 307 |
+
"eval_accuracy": 0.8320904498436372,
|
| 308 |
+
"eval_f1_macro": 0.7756514292421667,
|
| 309 |
+
"eval_f1_micro": 0.8320904498436372,
|
| 310 |
+
"eval_loss": 0.6163076162338257,
|
| 311 |
+
"eval_precision_macro": 0.776765552199579,
|
| 312 |
+
"eval_precision_micro": 0.8320904498436372,
|
| 313 |
+
"eval_recall_macro": 0.807685789299095,
|
| 314 |
+
"eval_recall_micro": 0.8320904498436372,
|
| 315 |
+
"eval_runtime": 78.0973,
|
| 316 |
+
"eval_samples_per_second": 53.228,
|
| 317 |
+
"eval_steps_per_second": 3.329,
|
| 318 |
+
"step": 1400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7285089849441476,
|
| 322 |
+
"grad_norm": 16.200693130493164,
|
| 323 |
+
"learning_rate": 1.635988343856241e-05,
|
| 324 |
+
"loss": 0.2738,
|
| 325 |
+
"step": 1500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7285089849441476,
|
| 329 |
+
"eval_accuracy": 0.8330526822227567,
|
| 330 |
+
"eval_f1_macro": 0.7657709635036466,
|
| 331 |
+
"eval_f1_micro": 0.8330526822227567,
|
| 332 |
+
"eval_loss": 0.5991656184196472,
|
| 333 |
+
"eval_precision_macro": 0.7896026550833485,
|
| 334 |
+
"eval_precision_micro": 0.8330526822227567,
|
| 335 |
+
"eval_recall_macro": 0.7825126366614965,
|
| 336 |
+
"eval_recall_micro": 0.8330526822227567,
|
| 337 |
+
"eval_runtime": 78.1674,
|
| 338 |
+
"eval_samples_per_second": 53.181,
|
| 339 |
+
"eval_steps_per_second": 3.326,
|
| 340 |
+
"step": 1500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.7770762506070908,
|
| 344 |
+
"grad_norm": 22.443140029907227,
|
| 345 |
+
"learning_rate": 1.6117047110247694e-05,
|
| 346 |
+
"loss": 0.2976,
|
| 347 |
+
"step": 1600
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.7770762506070908,
|
| 351 |
+
"eval_accuracy": 0.8277604041375992,
|
| 352 |
+
"eval_f1_macro": 0.7434375371463181,
|
| 353 |
+
"eval_f1_micro": 0.8277604041375993,
|
| 354 |
+
"eval_loss": 0.619115948677063,
|
| 355 |
+
"eval_precision_macro": 0.7596164331235828,
|
| 356 |
+
"eval_precision_micro": 0.8277604041375992,
|
| 357 |
+
"eval_recall_macro": 0.7832912830659067,
|
| 358 |
+
"eval_recall_micro": 0.8277604041375992,
|
| 359 |
+
"eval_runtime": 77.7196,
|
| 360 |
+
"eval_samples_per_second": 53.487,
|
| 361 |
+
"eval_steps_per_second": 3.345,
|
| 362 |
+
"step": 1600
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.825643516270034,
|
| 366 |
+
"grad_norm": 17.786861419677734,
|
| 367 |
+
"learning_rate": 1.587421078193298e-05,
|
| 368 |
+
"loss": 0.2914,
|
| 369 |
+
"step": 1700
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.825643516270034,
|
| 373 |
+
"eval_accuracy": 0.7873466442145778,
|
| 374 |
+
"eval_f1_macro": 0.7264208752916804,
|
| 375 |
+
"eval_f1_micro": 0.7873466442145777,
|
| 376 |
+
"eval_loss": 0.7651363015174866,
|
| 377 |
+
"eval_precision_macro": 0.7408201824968061,
|
| 378 |
+
"eval_precision_micro": 0.7873466442145778,
|
| 379 |
+
"eval_recall_macro": 0.7604117672744211,
|
| 380 |
+
"eval_recall_micro": 0.7873466442145778,
|
| 381 |
+
"eval_runtime": 77.8533,
|
| 382 |
+
"eval_samples_per_second": 53.395,
|
| 383 |
+
"eval_steps_per_second": 3.34,
|
| 384 |
+
"step": 1700
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8742107819329772,
|
| 388 |
+
"grad_norm": 15.827679634094238,
|
| 389 |
+
"learning_rate": 1.5631374453618262e-05,
|
| 390 |
+
"loss": 0.254,
|
| 391 |
+
"step": 1800
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.8742107819329772,
|
| 395 |
+
"eval_accuracy": 0.7729131585277844,
|
| 396 |
+
"eval_f1_macro": 0.7078131643612664,
|
| 397 |
+
"eval_f1_micro": 0.7729131585277844,
|
| 398 |
+
"eval_loss": 0.8441910743713379,
|
| 399 |
+
"eval_precision_macro": 0.7184265914939797,
|
| 400 |
+
"eval_precision_micro": 0.7729131585277844,
|
| 401 |
+
"eval_recall_macro": 0.7567655915669744,
|
| 402 |
+
"eval_recall_micro": 0.7729131585277844,
|
| 403 |
+
"eval_runtime": 78.4035,
|
| 404 |
+
"eval_samples_per_second": 53.021,
|
| 405 |
+
"eval_steps_per_second": 3.316,
|
| 406 |
+
"step": 1800
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.9227780475959203,
|
| 410 |
+
"grad_norm": 13.433658599853516,
|
| 411 |
+
"learning_rate": 1.5388538125303546e-05,
|
| 412 |
+
"loss": 0.2446,
|
| 413 |
+
"step": 1900
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.9227780475959203,
|
| 417 |
+
"eval_accuracy": 0.8330526822227567,
|
| 418 |
+
"eval_f1_macro": 0.7754170140757469,
|
| 419 |
+
"eval_f1_micro": 0.8330526822227567,
|
| 420 |
+
"eval_loss": 0.6231703162193298,
|
| 421 |
+
"eval_precision_macro": 0.7743561402393088,
|
| 422 |
+
"eval_precision_micro": 0.8330526822227567,
|
| 423 |
+
"eval_recall_macro": 0.8166841562149844,
|
| 424 |
+
"eval_recall_micro": 0.8330526822227567,
|
| 425 |
+
"eval_runtime": 77.9333,
|
| 426 |
+
"eval_samples_per_second": 53.341,
|
| 427 |
+
"eval_steps_per_second": 3.336,
|
| 428 |
+
"step": 1900
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.9713453132588635,
|
| 432 |
+
"grad_norm": 1.4447236061096191,
|
| 433 |
+
"learning_rate": 1.514570179698883e-05,
|
| 434 |
+
"loss": 0.2468,
|
| 435 |
+
"step": 2000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.9713453132588635,
|
| 439 |
+
"eval_accuracy": 0.8448400288669714,
|
| 440 |
+
"eval_f1_macro": 0.785930557684152,
|
| 441 |
+
"eval_f1_micro": 0.8448400288669714,
|
| 442 |
+
"eval_loss": 0.5916985869407654,
|
| 443 |
+
"eval_precision_macro": 0.779867107822518,
|
| 444 |
+
"eval_precision_micro": 0.8448400288669714,
|
| 445 |
+
"eval_recall_macro": 0.8258044114789991,
|
| 446 |
+
"eval_recall_micro": 0.8448400288669714,
|
| 447 |
+
"eval_runtime": 78.2704,
|
| 448 |
+
"eval_samples_per_second": 53.111,
|
| 449 |
+
"eval_steps_per_second": 3.322,
|
| 450 |
+
"step": 2000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0199125789218066,
|
| 454 |
+
"grad_norm": 42.209495544433594,
|
| 455 |
+
"learning_rate": 1.4902865468674114e-05,
|
| 456 |
+
"loss": 0.2197,
|
| 457 |
+
"step": 2100
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0199125789218066,
|
| 461 |
+
"eval_accuracy": 0.8210247774837623,
|
| 462 |
+
"eval_f1_macro": 0.7496958773425116,
|
| 463 |
+
"eval_f1_micro": 0.8210247774837625,
|
| 464 |
+
"eval_loss": 0.6304962038993835,
|
| 465 |
+
"eval_precision_macro": 0.7800275333894653,
|
| 466 |
+
"eval_precision_micro": 0.8210247774837623,
|
| 467 |
+
"eval_recall_macro": 0.7725863519296959,
|
| 468 |
+
"eval_recall_micro": 0.8210247774837623,
|
| 469 |
+
"eval_runtime": 78.4172,
|
| 470 |
+
"eval_samples_per_second": 53.011,
|
| 471 |
+
"eval_steps_per_second": 3.316,
|
| 472 |
+
"step": 2100
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0684798445847499,
|
| 476 |
+
"grad_norm": 6.323939800262451,
|
| 477 |
+
"learning_rate": 1.46600291403594e-05,
|
| 478 |
+
"loss": 0.1474,
|
| 479 |
+
"step": 2200
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0684798445847499,
|
| 483 |
+
"eval_accuracy": 0.8210247774837623,
|
| 484 |
+
"eval_f1_macro": 0.7654970298380952,
|
| 485 |
+
"eval_f1_micro": 0.8210247774837625,
|
| 486 |
+
"eval_loss": 0.6584117412567139,
|
| 487 |
+
"eval_precision_macro": 0.7776774908498755,
|
| 488 |
+
"eval_precision_micro": 0.8210247774837623,
|
| 489 |
+
"eval_recall_macro": 0.7832612508206293,
|
| 490 |
+
"eval_recall_micro": 0.8210247774837623,
|
| 491 |
+
"eval_runtime": 78.2294,
|
| 492 |
+
"eval_samples_per_second": 53.139,
|
| 493 |
+
"eval_steps_per_second": 3.324,
|
| 494 |
+
"step": 2200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.117047110247693,
|
| 498 |
+
"grad_norm": 5.200247287750244,
|
| 499 |
+
"learning_rate": 1.4417192812044682e-05,
|
| 500 |
+
"loss": 0.1385,
|
| 501 |
+
"step": 2300
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.117047110247693,
|
| 505 |
+
"eval_accuracy": 0.8465239355304306,
|
| 506 |
+
"eval_f1_macro": 0.795171009913394,
|
| 507 |
+
"eval_f1_micro": 0.8465239355304306,
|
| 508 |
+
"eval_loss": 0.5680557489395142,
|
| 509 |
+
"eval_precision_macro": 0.8036743010238906,
|
| 510 |
+
"eval_precision_micro": 0.8465239355304306,
|
| 511 |
+
"eval_recall_macro": 0.8194950943386284,
|
| 512 |
+
"eval_recall_micro": 0.8465239355304306,
|
| 513 |
+
"eval_runtime": 77.9399,
|
| 514 |
+
"eval_samples_per_second": 53.336,
|
| 515 |
+
"eval_steps_per_second": 3.336,
|
| 516 |
+
"step": 2300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.1656143759106363,
|
| 520 |
+
"grad_norm": 59.158382415771484,
|
| 521 |
+
"learning_rate": 1.4174356483729968e-05,
|
| 522 |
+
"loss": 0.1135,
|
| 523 |
+
"step": 2400
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.1656143759106363,
|
| 527 |
+
"eval_accuracy": 0.867452489776281,
|
| 528 |
+
"eval_f1_macro": 0.8221801724207984,
|
| 529 |
+
"eval_f1_micro": 0.867452489776281,
|
| 530 |
+
"eval_loss": 0.5212485194206238,
|
| 531 |
+
"eval_precision_macro": 0.8331447468612765,
|
| 532 |
+
"eval_precision_micro": 0.867452489776281,
|
| 533 |
+
"eval_recall_macro": 0.8320781071525781,
|
| 534 |
+
"eval_recall_micro": 0.867452489776281,
|
| 535 |
+
"eval_runtime": 78.3816,
|
| 536 |
+
"eval_samples_per_second": 53.035,
|
| 537 |
+
"eval_steps_per_second": 3.317,
|
| 538 |
+
"step": 2400
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.2141816415735793,
|
| 542 |
+
"grad_norm": 1.2092406749725342,
|
| 543 |
+
"learning_rate": 1.393152015541525e-05,
|
| 544 |
+
"loss": 0.153,
|
| 545 |
+
"step": 2500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.2141816415735793,
|
| 549 |
+
"eval_accuracy": 0.854462352658167,
|
| 550 |
+
"eval_f1_macro": 0.79162479913702,
|
| 551 |
+
"eval_f1_micro": 0.854462352658167,
|
| 552 |
+
"eval_loss": 0.5905571579933167,
|
| 553 |
+
"eval_precision_macro": 0.8007086193727224,
|
| 554 |
+
"eval_precision_micro": 0.854462352658167,
|
| 555 |
+
"eval_recall_macro": 0.8240486776141968,
|
| 556 |
+
"eval_recall_micro": 0.854462352658167,
|
| 557 |
+
"eval_runtime": 77.8377,
|
| 558 |
+
"eval_samples_per_second": 53.406,
|
| 559 |
+
"eval_steps_per_second": 3.34,
|
| 560 |
+
"step": 2500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.2627489072365226,
|
| 564 |
+
"grad_norm": 4.295379638671875,
|
| 565 |
+
"learning_rate": 1.3688683827100536e-05,
|
| 566 |
+
"loss": 0.1221,
|
| 567 |
+
"step": 2600
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.2627489072365226,
|
| 571 |
+
"eval_accuracy": 0.8780370459465962,
|
| 572 |
+
"eval_f1_macro": 0.8233792046483023,
|
| 573 |
+
"eval_f1_micro": 0.8780370459465962,
|
| 574 |
+
"eval_loss": 0.48117873072624207,
|
| 575 |
+
"eval_precision_macro": 0.8275579818555562,
|
| 576 |
+
"eval_precision_micro": 0.8780370459465962,
|
| 577 |
+
"eval_recall_macro": 0.8399965589517642,
|
| 578 |
+
"eval_recall_micro": 0.8780370459465962,
|
| 579 |
+
"eval_runtime": 78.2827,
|
| 580 |
+
"eval_samples_per_second": 53.102,
|
| 581 |
+
"eval_steps_per_second": 3.321,
|
| 582 |
+
"step": 2600
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.3113161728994658,
|
| 586 |
+
"grad_norm": 0.7493284940719604,
|
| 587 |
+
"learning_rate": 1.344584749878582e-05,
|
| 588 |
+
"loss": 0.134,
|
| 589 |
+
"step": 2700
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.3113161728994658,
|
| 593 |
+
"eval_accuracy": 0.8525378878999278,
|
| 594 |
+
"eval_f1_macro": 0.8105294018236757,
|
| 595 |
+
"eval_f1_micro": 0.8525378878999278,
|
| 596 |
+
"eval_loss": 0.6301819682121277,
|
| 597 |
+
"eval_precision_macro": 0.8127798645314742,
|
| 598 |
+
"eval_precision_micro": 0.8525378878999278,
|
| 599 |
+
"eval_recall_macro": 0.8407694300980793,
|
| 600 |
+
"eval_recall_micro": 0.8525378878999278,
|
| 601 |
+
"eval_runtime": 78.1792,
|
| 602 |
+
"eval_samples_per_second": 53.173,
|
| 603 |
+
"eval_steps_per_second": 3.326,
|
| 604 |
+
"step": 2700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.359883438562409,
|
| 608 |
+
"grad_norm": 15.269425392150879,
|
| 609 |
+
"learning_rate": 1.3203011170471102e-05,
|
| 610 |
+
"loss": 0.1177,
|
| 611 |
+
"step": 2800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.359883438562409,
|
| 615 |
+
"eval_accuracy": 0.8720230935770988,
|
| 616 |
+
"eval_f1_macro": 0.8162750069957628,
|
| 617 |
+
"eval_f1_micro": 0.872023093577099,
|
| 618 |
+
"eval_loss": 0.5413680672645569,
|
| 619 |
+
"eval_precision_macro": 0.8190184865925261,
|
| 620 |
+
"eval_precision_micro": 0.8720230935770988,
|
| 621 |
+
"eval_recall_macro": 0.8430994278929198,
|
| 622 |
+
"eval_recall_micro": 0.8720230935770988,
|
| 623 |
+
"eval_runtime": 77.9146,
|
| 624 |
+
"eval_samples_per_second": 53.353,
|
| 625 |
+
"eval_steps_per_second": 3.337,
|
| 626 |
+
"step": 2800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.408450704225352,
|
| 630 |
+
"grad_norm": 2.0257482528686523,
|
| 631 |
+
"learning_rate": 1.2960174842156388e-05,
|
| 632 |
+
"loss": 0.0987,
|
| 633 |
+
"step": 2900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.408450704225352,
|
| 637 |
+
"eval_accuracy": 0.8809237430839548,
|
| 638 |
+
"eval_f1_macro": 0.8218294114431427,
|
| 639 |
+
"eval_f1_micro": 0.8809237430839548,
|
| 640 |
+
"eval_loss": 0.5116602182388306,
|
| 641 |
+
"eval_precision_macro": 0.8136201153530077,
|
| 642 |
+
"eval_precision_micro": 0.8809237430839548,
|
| 643 |
+
"eval_recall_macro": 0.8508023667833765,
|
| 644 |
+
"eval_recall_micro": 0.8809237430839548,
|
| 645 |
+
"eval_runtime": 78.002,
|
| 646 |
+
"eval_samples_per_second": 53.294,
|
| 647 |
+
"eval_steps_per_second": 3.333,
|
| 648 |
+
"step": 2900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.4570179698882952,
|
| 652 |
+
"grad_norm": 42.31605529785156,
|
| 653 |
+
"learning_rate": 1.2717338513841673e-05,
|
| 654 |
+
"loss": 0.1058,
|
| 655 |
+
"step": 3000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.4570179698882952,
|
| 659 |
+
"eval_accuracy": 0.8433966802982921,
|
| 660 |
+
"eval_f1_macro": 0.8068375038460742,
|
| 661 |
+
"eval_f1_micro": 0.8433966802982921,
|
| 662 |
+
"eval_loss": 0.6526976823806763,
|
| 663 |
+
"eval_precision_macro": 0.8158791028657807,
|
| 664 |
+
"eval_precision_micro": 0.8433966802982921,
|
| 665 |
+
"eval_recall_macro": 0.8236984397615126,
|
| 666 |
+
"eval_recall_micro": 0.8433966802982921,
|
| 667 |
+
"eval_runtime": 78.2408,
|
| 668 |
+
"eval_samples_per_second": 53.131,
|
| 669 |
+
"eval_steps_per_second": 3.323,
|
| 670 |
+
"step": 3000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.5055852355512385,
|
| 674 |
+
"grad_norm": 0.04906897246837616,
|
| 675 |
+
"learning_rate": 1.2474502185526956e-05,
|
| 676 |
+
"loss": 0.0847,
|
| 677 |
+
"step": 3100
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.5055852355512385,
|
| 681 |
+
"eval_accuracy": 0.8554245850372865,
|
| 682 |
+
"eval_f1_macro": 0.798783246253302,
|
| 683 |
+
"eval_f1_micro": 0.8554245850372865,
|
| 684 |
+
"eval_loss": 0.5800924301147461,
|
| 685 |
+
"eval_precision_macro": 0.8004222933889796,
|
| 686 |
+
"eval_precision_micro": 0.8554245850372865,
|
| 687 |
+
"eval_recall_macro": 0.8243767820708686,
|
| 688 |
+
"eval_recall_micro": 0.8554245850372865,
|
| 689 |
+
"eval_runtime": 77.9481,
|
| 690 |
+
"eval_samples_per_second": 53.33,
|
| 691 |
+
"eval_steps_per_second": 3.336,
|
| 692 |
+
"step": 3100
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.5541525012141817,
|
| 696 |
+
"grad_norm": 0.13342243432998657,
|
| 697 |
+
"learning_rate": 1.223166585721224e-05,
|
| 698 |
+
"loss": 0.0934,
|
| 699 |
+
"step": 3200
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.5541525012141817,
|
| 703 |
+
"eval_accuracy": 0.8433966802982921,
|
| 704 |
+
"eval_f1_macro": 0.7975033136779321,
|
| 705 |
+
"eval_f1_micro": 0.8433966802982921,
|
| 706 |
+
"eval_loss": 0.6552587151527405,
|
| 707 |
+
"eval_precision_macro": 0.7929638472956879,
|
| 708 |
+
"eval_precision_micro": 0.8433966802982921,
|
| 709 |
+
"eval_recall_macro": 0.8272082545582277,
|
| 710 |
+
"eval_recall_micro": 0.8433966802982921,
|
| 711 |
+
"eval_runtime": 78.5124,
|
| 712 |
+
"eval_samples_per_second": 52.947,
|
| 713 |
+
"eval_steps_per_second": 3.312,
|
| 714 |
+
"step": 3200
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.602719766877125,
|
| 718 |
+
"grad_norm": 0.7083119750022888,
|
| 719 |
+
"learning_rate": 1.1988829528897524e-05,
|
| 720 |
+
"loss": 0.0969,
|
| 721 |
+
"step": 3300
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.602719766877125,
|
| 725 |
+
"eval_accuracy": 0.82607649747414,
|
| 726 |
+
"eval_f1_macro": 0.7832101352133586,
|
| 727 |
+
"eval_f1_micro": 0.82607649747414,
|
| 728 |
+
"eval_loss": 0.7666494250297546,
|
| 729 |
+
"eval_precision_macro": 0.7876268324182853,
|
| 730 |
+
"eval_precision_micro": 0.82607649747414,
|
| 731 |
+
"eval_recall_macro": 0.8241865106118899,
|
| 732 |
+
"eval_recall_micro": 0.82607649747414,
|
| 733 |
+
"eval_runtime": 78.311,
|
| 734 |
+
"eval_samples_per_second": 53.083,
|
| 735 |
+
"eval_steps_per_second": 3.32,
|
| 736 |
+
"step": 3300
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.651287032540068,
|
| 740 |
+
"grad_norm": 16.786699295043945,
|
| 741 |
+
"learning_rate": 1.1745993200582808e-05,
|
| 742 |
+
"loss": 0.1428,
|
| 743 |
+
"step": 3400
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.651287032540068,
|
| 747 |
+
"eval_accuracy": 0.8462833774356507,
|
| 748 |
+
"eval_f1_macro": 0.7894688554105801,
|
| 749 |
+
"eval_f1_micro": 0.8462833774356507,
|
| 750 |
+
"eval_loss": 0.685663104057312,
|
| 751 |
+
"eval_precision_macro": 0.7989143890731024,
|
| 752 |
+
"eval_precision_micro": 0.8462833774356507,
|
| 753 |
+
"eval_recall_macro": 0.8135123764257445,
|
| 754 |
+
"eval_recall_micro": 0.8462833774356507,
|
| 755 |
+
"eval_runtime": 78.0482,
|
| 756 |
+
"eval_samples_per_second": 53.262,
|
| 757 |
+
"eval_steps_per_second": 3.331,
|
| 758 |
+
"step": 3400
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.6998542982030111,
|
| 762 |
+
"grad_norm": 27.461700439453125,
|
| 763 |
+
"learning_rate": 1.1503156872268093e-05,
|
| 764 |
+
"loss": 0.0681,
|
| 765 |
+
"step": 3500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.6998542982030111,
|
| 769 |
+
"eval_accuracy": 0.8898243925908107,
|
| 770 |
+
"eval_f1_macro": 0.8280214132166845,
|
| 771 |
+
"eval_f1_micro": 0.8898243925908107,
|
| 772 |
+
"eval_loss": 0.5203650593757629,
|
| 773 |
+
"eval_precision_macro": 0.8341272420720794,
|
| 774 |
+
"eval_precision_micro": 0.8898243925908107,
|
| 775 |
+
"eval_recall_macro": 0.8595091501105108,
|
| 776 |
+
"eval_recall_micro": 0.8898243925908107,
|
| 777 |
+
"eval_runtime": 78.1461,
|
| 778 |
+
"eval_samples_per_second": 53.195,
|
| 779 |
+
"eval_steps_per_second": 3.327,
|
| 780 |
+
"step": 3500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.7484215638659544,
|
| 784 |
+
"grad_norm": 69.4913101196289,
|
| 785 |
+
"learning_rate": 1.1260320543953375e-05,
|
| 786 |
+
"loss": 0.0931,
|
| 787 |
+
"step": 3600
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.7484215638659544,
|
| 791 |
+
"eval_accuracy": 0.8684147221554005,
|
| 792 |
+
"eval_f1_macro": 0.8151692727718802,
|
| 793 |
+
"eval_f1_micro": 0.8684147221554005,
|
| 794 |
+
"eval_loss": 0.6120151281356812,
|
| 795 |
+
"eval_precision_macro": 0.8240793067449873,
|
| 796 |
+
"eval_precision_micro": 0.8684147221554005,
|
| 797 |
+
"eval_recall_macro": 0.8314024627761833,
|
| 798 |
+
"eval_recall_micro": 0.8684147221554005,
|
| 799 |
+
"eval_runtime": 78.1922,
|
| 800 |
+
"eval_samples_per_second": 53.164,
|
| 801 |
+
"eval_steps_per_second": 3.325,
|
| 802 |
+
"step": 3600
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7969888295288974,
|
| 806 |
+
"grad_norm": 0.8026056885719299,
|
| 807 |
+
"learning_rate": 1.1017484215638661e-05,
|
| 808 |
+
"loss": 0.0935,
|
| 809 |
+
"step": 3700
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.7969888295288974,
|
| 813 |
+
"eval_accuracy": 0.8715419773875391,
|
| 814 |
+
"eval_f1_macro": 0.8220476579310915,
|
| 815 |
+
"eval_f1_micro": 0.8715419773875391,
|
| 816 |
+
"eval_loss": 0.5801733732223511,
|
| 817 |
+
"eval_precision_macro": 0.8170628217436031,
|
| 818 |
+
"eval_precision_micro": 0.8715419773875391,
|
| 819 |
+
"eval_recall_macro": 0.8414628001544893,
|
| 820 |
+
"eval_recall_micro": 0.8715419773875391,
|
| 821 |
+
"eval_runtime": 77.92,
|
| 822 |
+
"eval_samples_per_second": 53.35,
|
| 823 |
+
"eval_steps_per_second": 3.337,
|
| 824 |
+
"step": 3700
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.8455560951918408,
|
| 828 |
+
"grad_norm": 20.50851058959961,
|
| 829 |
+
"learning_rate": 1.0774647887323943e-05,
|
| 830 |
+
"loss": 0.1051,
|
| 831 |
+
"step": 3800
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.8455560951918408,
|
| 835 |
+
"eval_accuracy": 0.8638441183545826,
|
| 836 |
+
"eval_f1_macro": 0.8138781743364819,
|
| 837 |
+
"eval_f1_micro": 0.8638441183545826,
|
| 838 |
+
"eval_loss": 0.6387995481491089,
|
| 839 |
+
"eval_precision_macro": 0.8120807002790287,
|
| 840 |
+
"eval_precision_micro": 0.8638441183545826,
|
| 841 |
+
"eval_recall_macro": 0.8384780204857788,
|
| 842 |
+
"eval_recall_micro": 0.8638441183545826,
|
| 843 |
+
"eval_runtime": 78.3578,
|
| 844 |
+
"eval_samples_per_second": 53.052,
|
| 845 |
+
"eval_steps_per_second": 3.318,
|
| 846 |
+
"step": 3800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.8941233608547838,
|
| 850 |
+
"grad_norm": 0.4359864890575409,
|
| 851 |
+
"learning_rate": 1.0531811559009229e-05,
|
| 852 |
+
"loss": 0.1141,
|
| 853 |
+
"step": 3900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.8941233608547838,
|
| 857 |
+
"eval_accuracy": 0.8734664421457782,
|
| 858 |
+
"eval_f1_macro": 0.8181325108037866,
|
| 859 |
+
"eval_f1_micro": 0.8734664421457783,
|
| 860 |
+
"eval_loss": 0.6033037304878235,
|
| 861 |
+
"eval_precision_macro": 0.8257092361144394,
|
| 862 |
+
"eval_precision_micro": 0.8734664421457782,
|
| 863 |
+
"eval_recall_macro": 0.8280682968840635,
|
| 864 |
+
"eval_recall_micro": 0.8734664421457782,
|
| 865 |
+
"eval_runtime": 78.3807,
|
| 866 |
+
"eval_samples_per_second": 53.036,
|
| 867 |
+
"eval_steps_per_second": 3.317,
|
| 868 |
+
"step": 3900
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.942690626517727,
|
| 872 |
+
"grad_norm": 0.026569893583655357,
|
| 873 |
+
"learning_rate": 1.0288975230694513e-05,
|
| 874 |
+
"loss": 0.0782,
|
| 875 |
+
"step": 4000
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.942690626517727,
|
| 879 |
+
"eval_accuracy": 0.8713014192927592,
|
| 880 |
+
"eval_f1_macro": 0.8158890342266224,
|
| 881 |
+
"eval_f1_micro": 0.8713014192927592,
|
| 882 |
+
"eval_loss": 0.6082781553268433,
|
| 883 |
+
"eval_precision_macro": 0.8100721903094688,
|
| 884 |
+
"eval_precision_micro": 0.8713014192927592,
|
| 885 |
+
"eval_recall_macro": 0.8378298843929596,
|
| 886 |
+
"eval_recall_micro": 0.8713014192927592,
|
| 887 |
+
"eval_runtime": 77.7827,
|
| 888 |
+
"eval_samples_per_second": 53.444,
|
| 889 |
+
"eval_steps_per_second": 3.343,
|
| 890 |
+
"step": 4000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.9912578921806703,
|
| 894 |
+
"grad_norm": 0.27337446808815,
|
| 895 |
+
"learning_rate": 1.0046138902379797e-05,
|
| 896 |
+
"loss": 0.0935,
|
| 897 |
+
"step": 4100
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.9912578921806703,
|
| 901 |
+
"eval_accuracy": 0.8385855184026942,
|
| 902 |
+
"eval_f1_macro": 0.7755030296607576,
|
| 903 |
+
"eval_f1_micro": 0.8385855184026941,
|
| 904 |
+
"eval_loss": 0.7882886528968811,
|
| 905 |
+
"eval_precision_macro": 0.772528897611925,
|
| 906 |
+
"eval_precision_micro": 0.8385855184026942,
|
| 907 |
+
"eval_recall_macro": 0.821396700276969,
|
| 908 |
+
"eval_recall_micro": 0.8385855184026942,
|
| 909 |
+
"eval_runtime": 78.0832,
|
| 910 |
+
"eval_samples_per_second": 53.238,
|
| 911 |
+
"eval_steps_per_second": 3.33,
|
| 912 |
+
"step": 4100
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.0398251578436133,
|
| 916 |
+
"grad_norm": 0.06082015484571457,
|
| 917 |
+
"learning_rate": 9.803302574065081e-06,
|
| 918 |
+
"loss": 0.0446,
|
| 919 |
+
"step": 4200
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.0398251578436133,
|
| 923 |
+
"eval_accuracy": 0.8462833774356507,
|
| 924 |
+
"eval_f1_macro": 0.793800305134788,
|
| 925 |
+
"eval_f1_micro": 0.8462833774356507,
|
| 926 |
+
"eval_loss": 0.7242459654808044,
|
| 927 |
+
"eval_precision_macro": 0.8042449609141427,
|
| 928 |
+
"eval_precision_micro": 0.8462833774356507,
|
| 929 |
+
"eval_recall_macro": 0.8070235910631676,
|
| 930 |
+
"eval_recall_micro": 0.8462833774356507,
|
| 931 |
+
"eval_runtime": 78.366,
|
| 932 |
+
"eval_samples_per_second": 53.046,
|
| 933 |
+
"eval_steps_per_second": 3.318,
|
| 934 |
+
"step": 4200
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.0883924235065567,
|
| 938 |
+
"grad_norm": 1.1284111738204956,
|
| 939 |
+
"learning_rate": 9.560466245750365e-06,
|
| 940 |
+
"loss": 0.0394,
|
| 941 |
+
"step": 4300
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.0883924235065567,
|
| 945 |
+
"eval_accuracy": 0.8573490497955256,
|
| 946 |
+
"eval_f1_macro": 0.8097667721853947,
|
| 947 |
+
"eval_f1_micro": 0.8573490497955256,
|
| 948 |
+
"eval_loss": 0.6780639886856079,
|
| 949 |
+
"eval_precision_macro": 0.8206783431890832,
|
| 950 |
+
"eval_precision_micro": 0.8573490497955256,
|
| 951 |
+
"eval_recall_macro": 0.8218729335160754,
|
| 952 |
+
"eval_recall_micro": 0.8573490497955256,
|
| 953 |
+
"eval_runtime": 78.4567,
|
| 954 |
+
"eval_samples_per_second": 52.985,
|
| 955 |
+
"eval_steps_per_second": 3.314,
|
| 956 |
+
"step": 4300
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.1369596891694997,
|
| 960 |
+
"grad_norm": 1.0478459596633911,
|
| 961 |
+
"learning_rate": 9.317629917435649e-06,
|
| 962 |
+
"loss": 0.023,
|
| 963 |
+
"step": 4400
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.1369596891694997,
|
| 967 |
+
"eval_accuracy": 0.8381044022131344,
|
| 968 |
+
"eval_f1_macro": 0.7761721486362632,
|
| 969 |
+
"eval_f1_micro": 0.8381044022131344,
|
| 970 |
+
"eval_loss": 0.8235397934913635,
|
| 971 |
+
"eval_precision_macro": 0.8022053549256318,
|
| 972 |
+
"eval_precision_micro": 0.8381044022131344,
|
| 973 |
+
"eval_recall_macro": 0.8109538575923662,
|
| 974 |
+
"eval_recall_micro": 0.8381044022131344,
|
| 975 |
+
"eval_runtime": 77.944,
|
| 976 |
+
"eval_samples_per_second": 53.333,
|
| 977 |
+
"eval_steps_per_second": 3.336,
|
| 978 |
+
"step": 4400
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1855269548324427,
|
| 982 |
+
"grad_norm": 0.0286689605563879,
|
| 983 |
+
"learning_rate": 9.074793589120935e-06,
|
| 984 |
+
"loss": 0.0338,
|
| 985 |
+
"step": 4500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.1855269548324427,
|
| 989 |
+
"eval_accuracy": 0.8703391869136397,
|
| 990 |
+
"eval_f1_macro": 0.8094122567680977,
|
| 991 |
+
"eval_f1_micro": 0.8703391869136397,
|
| 992 |
+
"eval_loss": 0.6315681338310242,
|
| 993 |
+
"eval_precision_macro": 0.8074299681427781,
|
| 994 |
+
"eval_precision_micro": 0.8703391869136397,
|
| 995 |
+
"eval_recall_macro": 0.8337866144492019,
|
| 996 |
+
"eval_recall_micro": 0.8703391869136397,
|
| 997 |
+
"eval_runtime": 78.3498,
|
| 998 |
+
"eval_samples_per_second": 53.057,
|
| 999 |
+
"eval_steps_per_second": 3.318,
|
| 1000 |
+
"step": 4500
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.234094220495386,
|
| 1004 |
+
"grad_norm": 0.06468763947486877,
|
| 1005 |
+
"learning_rate": 8.831957260806217e-06,
|
| 1006 |
+
"loss": 0.0414,
|
| 1007 |
+
"step": 4600
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.234094220495386,
|
| 1011 |
+
"eval_accuracy": 0.8840509983160934,
|
| 1012 |
+
"eval_f1_macro": 0.824537485440517,
|
| 1013 |
+
"eval_f1_micro": 0.8840509983160935,
|
| 1014 |
+
"eval_loss": 0.5948061347007751,
|
| 1015 |
+
"eval_precision_macro": 0.8233324585853661,
|
| 1016 |
+
"eval_precision_micro": 0.8840509983160934,
|
| 1017 |
+
"eval_recall_macro": 0.8505518969806567,
|
| 1018 |
+
"eval_recall_micro": 0.8840509983160934,
|
| 1019 |
+
"eval_runtime": 77.9733,
|
| 1020 |
+
"eval_samples_per_second": 53.313,
|
| 1021 |
+
"eval_steps_per_second": 3.334,
|
| 1022 |
+
"step": 4600
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.282661486158329,
|
| 1026 |
+
"grad_norm": 4.641617298126221,
|
| 1027 |
+
"learning_rate": 8.5891209324915e-06,
|
| 1028 |
+
"loss": 0.0379,
|
| 1029 |
+
"step": 4700
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.282661486158329,
|
| 1033 |
+
"eval_accuracy": 0.8765936973779168,
|
| 1034 |
+
"eval_f1_macro": 0.825230740105461,
|
| 1035 |
+
"eval_f1_micro": 0.8765936973779168,
|
| 1036 |
+
"eval_loss": 0.5780928134918213,
|
| 1037 |
+
"eval_precision_macro": 0.8206894619069279,
|
| 1038 |
+
"eval_precision_micro": 0.8765936973779168,
|
| 1039 |
+
"eval_recall_macro": 0.841894179116351,
|
| 1040 |
+
"eval_recall_micro": 0.8765936973779168,
|
| 1041 |
+
"eval_runtime": 78.4226,
|
| 1042 |
+
"eval_samples_per_second": 53.008,
|
| 1043 |
+
"eval_steps_per_second": 3.315,
|
| 1044 |
+
"step": 4700
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.3312287518212726,
|
| 1048 |
+
"grad_norm": 0.23332637548446655,
|
| 1049 |
+
"learning_rate": 8.346284604176785e-06,
|
| 1050 |
+
"loss": 0.0473,
|
| 1051 |
+
"step": 4800
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.3312287518212726,
|
| 1055 |
+
"eval_accuracy": 0.8729853259562185,
|
| 1056 |
+
"eval_f1_macro": 0.8052063570572925,
|
| 1057 |
+
"eval_f1_micro": 0.8729853259562185,
|
| 1058 |
+
"eval_loss": 0.6347105503082275,
|
| 1059 |
+
"eval_precision_macro": 0.8294626941554183,
|
| 1060 |
+
"eval_precision_micro": 0.8729853259562185,
|
| 1061 |
+
"eval_recall_macro": 0.8174296733333687,
|
| 1062 |
+
"eval_recall_micro": 0.8729853259562185,
|
| 1063 |
+
"eval_runtime": 77.9725,
|
| 1064 |
+
"eval_samples_per_second": 53.314,
|
| 1065 |
+
"eval_steps_per_second": 3.335,
|
| 1066 |
+
"step": 4800
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.3797960174842157,
|
| 1070 |
+
"grad_norm": 0.014487605541944504,
|
| 1071 |
+
"learning_rate": 8.103448275862069e-06,
|
| 1072 |
+
"loss": 0.0159,
|
| 1073 |
+
"step": 4900
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.3797960174842157,
|
| 1077 |
+
"eval_accuracy": 0.8681741640606206,
|
| 1078 |
+
"eval_f1_macro": 0.8094189525603713,
|
| 1079 |
+
"eval_f1_micro": 0.8681741640606206,
|
| 1080 |
+
"eval_loss": 0.6882294416427612,
|
| 1081 |
+
"eval_precision_macro": 0.8262511053264366,
|
| 1082 |
+
"eval_precision_micro": 0.8681741640606206,
|
| 1083 |
+
"eval_recall_macro": 0.824772348858174,
|
| 1084 |
+
"eval_recall_micro": 0.8681741640606206,
|
| 1085 |
+
"eval_runtime": 78.4876,
|
| 1086 |
+
"eval_samples_per_second": 52.964,
|
| 1087 |
+
"eval_steps_per_second": 3.313,
|
| 1088 |
+
"step": 4900
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.4283632831471587,
|
| 1092 |
+
"grad_norm": 0.011654403060674667,
|
| 1093 |
+
"learning_rate": 7.860611947547354e-06,
|
| 1094 |
+
"loss": 0.0115,
|
| 1095 |
+
"step": 5000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.4283632831471587,
|
| 1099 |
+
"eval_accuracy": 0.8830887659369738,
|
| 1100 |
+
"eval_f1_macro": 0.8288533499086042,
|
| 1101 |
+
"eval_f1_micro": 0.8830887659369738,
|
| 1102 |
+
"eval_loss": 0.5934479832649231,
|
| 1103 |
+
"eval_precision_macro": 0.8396603529798649,
|
| 1104 |
+
"eval_precision_micro": 0.8830887659369738,
|
| 1105 |
+
"eval_recall_macro": 0.8453069551945437,
|
| 1106 |
+
"eval_recall_micro": 0.8830887659369738,
|
| 1107 |
+
"eval_runtime": 78.5682,
|
| 1108 |
+
"eval_samples_per_second": 52.909,
|
| 1109 |
+
"eval_steps_per_second": 3.309,
|
| 1110 |
+
"step": 5000
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.476930548810102,
|
| 1114 |
+
"grad_norm": 21.12113380432129,
|
| 1115 |
+
"learning_rate": 7.617775619232638e-06,
|
| 1116 |
+
"loss": 0.0494,
|
| 1117 |
+
"step": 5100
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.476930548810102,
|
| 1121 |
+
"eval_accuracy": 0.8506134231416888,
|
| 1122 |
+
"eval_f1_macro": 0.7896669170968705,
|
| 1123 |
+
"eval_f1_micro": 0.8506134231416888,
|
| 1124 |
+
"eval_loss": 0.732039749622345,
|
| 1125 |
+
"eval_precision_macro": 0.7898243286153485,
|
| 1126 |
+
"eval_precision_micro": 0.8506134231416888,
|
| 1127 |
+
"eval_recall_macro": 0.8132701383447537,
|
| 1128 |
+
"eval_recall_micro": 0.8506134231416888,
|
| 1129 |
+
"eval_runtime": 78.0419,
|
| 1130 |
+
"eval_samples_per_second": 53.266,
|
| 1131 |
+
"eval_steps_per_second": 3.332,
|
| 1132 |
+
"step": 5100
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.525497814473045,
|
| 1136 |
+
"grad_norm": 0.14766599237918854,
|
| 1137 |
+
"learning_rate": 7.3749392909179215e-06,
|
| 1138 |
+
"loss": 0.0318,
|
| 1139 |
+
"step": 5200
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.525497814473045,
|
| 1143 |
+
"eval_accuracy": 0.8491700745730094,
|
| 1144 |
+
"eval_f1_macro": 0.8013080246715508,
|
| 1145 |
+
"eval_f1_micro": 0.8491700745730094,
|
| 1146 |
+
"eval_loss": 0.775058925151825,
|
| 1147 |
+
"eval_precision_macro": 0.8191511470633912,
|
| 1148 |
+
"eval_precision_micro": 0.8491700745730094,
|
| 1149 |
+
"eval_recall_macro": 0.8104006475463327,
|
| 1150 |
+
"eval_recall_micro": 0.8491700745730094,
|
| 1151 |
+
"eval_runtime": 78.0698,
|
| 1152 |
+
"eval_samples_per_second": 53.247,
|
| 1153 |
+
"eval_steps_per_second": 3.33,
|
| 1154 |
+
"step": 5200
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.5740650801359886,
|
| 1158 |
+
"grad_norm": 0.01593843102455139,
|
| 1159 |
+
"learning_rate": 7.1321029626032054e-06,
|
| 1160 |
+
"loss": 0.0493,
|
| 1161 |
+
"step": 5300
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.5740650801359886,
|
| 1165 |
+
"eval_accuracy": 0.8907866249699302,
|
| 1166 |
+
"eval_f1_macro": 0.846949212010463,
|
| 1167 |
+
"eval_f1_micro": 0.8907866249699302,
|
| 1168 |
+
"eval_loss": 0.5424800515174866,
|
| 1169 |
+
"eval_precision_macro": 0.8565661804143393,
|
| 1170 |
+
"eval_precision_micro": 0.8907866249699302,
|
| 1171 |
+
"eval_recall_macro": 0.852065989778345,
|
| 1172 |
+
"eval_recall_micro": 0.8907866249699302,
|
| 1173 |
+
"eval_runtime": 78.4856,
|
| 1174 |
+
"eval_samples_per_second": 52.965,
|
| 1175 |
+
"eval_steps_per_second": 3.313,
|
| 1176 |
+
"step": 5300
|
| 1177 |
+
}
|
| 1178 |
+
],
|
| 1179 |
+
"logging_steps": 100,
|
| 1180 |
+
"max_steps": 8236,
|
| 1181 |
+
"num_input_tokens_seen": 0,
|
| 1182 |
+
"num_train_epochs": 4,
|
| 1183 |
+
"save_steps": 100,
|
| 1184 |
+
"stateful_callbacks": {
|
| 1185 |
+
"TrainerControl": {
|
| 1186 |
+
"args": {
|
| 1187 |
+
"should_epoch_stop": false,
|
| 1188 |
+
"should_evaluate": false,
|
| 1189 |
+
"should_log": false,
|
| 1190 |
+
"should_save": true,
|
| 1191 |
+
"should_training_stop": false
|
| 1192 |
+
},
|
| 1193 |
+
"attributes": {}
|
| 1194 |
+
}
|
| 1195 |
+
},
|
| 1196 |
+
"total_flos": 2.231404480620749e+16,
|
| 1197 |
+
"train_batch_size": 16,
|
| 1198 |
+
"trial_name": null,
|
| 1199 |
+
"trial_params": null
|
| 1200 |
+
}
|
checkpoint-5300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81185f838ff4005f143cdc05247881e3041d333be8afba1fe331ee011795371e
|
| 3 |
+
size 5304
|
checkpoint-5300/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8236/config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_10": 10,
|
| 40 |
+
"LABEL_11": 11,
|
| 41 |
+
"LABEL_12": 12,
|
| 42 |
+
"LABEL_13": 13,
|
| 43 |
+
"LABEL_14": 14,
|
| 44 |
+
"LABEL_15": 15,
|
| 45 |
+
"LABEL_16": 16,
|
| 46 |
+
"LABEL_17": 17,
|
| 47 |
+
"LABEL_18": 18,
|
| 48 |
+
"LABEL_19": 19,
|
| 49 |
+
"LABEL_2": 2,
|
| 50 |
+
"LABEL_20": 20,
|
| 51 |
+
"LABEL_3": 3,
|
| 52 |
+
"LABEL_4": 4,
|
| 53 |
+
"LABEL_5": 5,
|
| 54 |
+
"LABEL_6": 6,
|
| 55 |
+
"LABEL_7": 7,
|
| 56 |
+
"LABEL_8": 8,
|
| 57 |
+
"LABEL_9": 9
|
| 58 |
+
},
|
| 59 |
+
"layer_norm_eps": 1e-12,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"model_type": "bert",
|
| 62 |
+
"num_attention_heads": 12,
|
| 63 |
+
"num_hidden_layers": 12,
|
| 64 |
+
"pad_token_id": 0,
|
| 65 |
+
"position_embedding_type": "absolute",
|
| 66 |
+
"problem_type": "single_label_classification",
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.52.4",
|
| 69 |
+
"type_vocab_size": 2,
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 30000
|
| 72 |
+
}
|
checkpoint-8236/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3ef485cdaa24383d6f4d60fb34175bc76a4ad13cae0233f9f9ff93b52a76482
|
| 3 |
+
size 436413500
|
checkpoint-8236/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:920f3abd184297707940170c170e35236f2ba62d2a4d1886f5a6f7e2b559313d
|
| 3 |
+
size 872948026
|
checkpoint-8236/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea3e0c86e848e8bd83e087b4b490662835b7687a93c2a89a36e068037a31ad59
|
| 3 |
+
size 14244
|
checkpoint-8236/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c49c4c3f9280587c8ffc7eba095e0030369b0c09f7ff72035d62a66e48c3f2d2
|
| 3 |
+
size 1064
|
checkpoint-8236/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-8236/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8236/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-8236/trainer_state.json
ADDED
|
@@ -0,0 +1,1838 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 5300,
|
| 3 |
+
"best_metric": 0.846949212010463,
|
| 4 |
+
"best_model_checkpoint": "./camelbert-ner-author/checkpoint-5300",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 8236,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04856726566294318,
|
| 14 |
+
"grad_norm": 13.77788257598877,
|
| 15 |
+
"learning_rate": 1.9759592034968435e-05,
|
| 16 |
+
"loss": 2.5655,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04856726566294318,
|
| 21 |
+
"eval_accuracy": 0.4197738753909069,
|
| 22 |
+
"eval_f1_macro": 0.3205328980120634,
|
| 23 |
+
"eval_f1_micro": 0.4197738753909069,
|
| 24 |
+
"eval_loss": 2.164029121398926,
|
| 25 |
+
"eval_precision_macro": 0.42432855880852344,
|
| 26 |
+
"eval_precision_micro": 0.4197738753909069,
|
| 27 |
+
"eval_recall_macro": 0.39236584110181216,
|
| 28 |
+
"eval_recall_micro": 0.4197738753909069,
|
| 29 |
+
"eval_runtime": 77.4428,
|
| 30 |
+
"eval_samples_per_second": 53.678,
|
| 31 |
+
"eval_steps_per_second": 3.357,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09713453132588636,
|
| 36 |
+
"grad_norm": 11.284036636352539,
|
| 37 |
+
"learning_rate": 1.9516755706653716e-05,
|
| 38 |
+
"loss": 1.7809,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.09713453132588636,
|
| 43 |
+
"eval_accuracy": 0.5876834255472697,
|
| 44 |
+
"eval_f1_macro": 0.5021998875928434,
|
| 45 |
+
"eval_f1_micro": 0.5876834255472697,
|
| 46 |
+
"eval_loss": 1.547103762626648,
|
| 47 |
+
"eval_precision_macro": 0.5640550767871323,
|
| 48 |
+
"eval_precision_micro": 0.5876834255472697,
|
| 49 |
+
"eval_recall_macro": 0.5447230363092859,
|
| 50 |
+
"eval_recall_micro": 0.5876834255472697,
|
| 51 |
+
"eval_runtime": 77.3875,
|
| 52 |
+
"eval_samples_per_second": 53.717,
|
| 53 |
+
"eval_steps_per_second": 3.36,
|
| 54 |
+
"step": 200
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.14570179698882954,
|
| 58 |
+
"grad_norm": 15.53082275390625,
|
| 59 |
+
"learning_rate": 1.9273919378339e-05,
|
| 60 |
+
"loss": 1.2903,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.14570179698882954,
|
| 65 |
+
"eval_accuracy": 0.6300216502285302,
|
| 66 |
+
"eval_f1_macro": 0.5639062324413268,
|
| 67 |
+
"eval_f1_micro": 0.6300216502285302,
|
| 68 |
+
"eval_loss": 1.3453640937805176,
|
| 69 |
+
"eval_precision_macro": 0.5883696452747289,
|
| 70 |
+
"eval_precision_micro": 0.6300216502285302,
|
| 71 |
+
"eval_recall_macro": 0.6245065052027649,
|
| 72 |
+
"eval_recall_micro": 0.6300216502285302,
|
| 73 |
+
"eval_runtime": 77.7169,
|
| 74 |
+
"eval_samples_per_second": 53.489,
|
| 75 |
+
"eval_steps_per_second": 3.345,
|
| 76 |
+
"step": 300
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.1942690626517727,
|
| 80 |
+
"grad_norm": 12.855542182922363,
|
| 81 |
+
"learning_rate": 1.9031083050024287e-05,
|
| 82 |
+
"loss": 1.0303,
|
| 83 |
+
"step": 400
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.1942690626517727,
|
| 87 |
+
"eval_accuracy": 0.6980995910512389,
|
| 88 |
+
"eval_f1_macro": 0.621757249063289,
|
| 89 |
+
"eval_f1_micro": 0.6980995910512389,
|
| 90 |
+
"eval_loss": 1.0540422201156616,
|
| 91 |
+
"eval_precision_macro": 0.6363865097952114,
|
| 92 |
+
"eval_precision_micro": 0.6980995910512389,
|
| 93 |
+
"eval_recall_macro": 0.6615766427269236,
|
| 94 |
+
"eval_recall_micro": 0.6980995910512389,
|
| 95 |
+
"eval_runtime": 78.209,
|
| 96 |
+
"eval_samples_per_second": 53.152,
|
| 97 |
+
"eval_steps_per_second": 3.324,
|
| 98 |
+
"step": 400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.24283632831471588,
|
| 102 |
+
"grad_norm": 13.974908828735352,
|
| 103 |
+
"learning_rate": 1.8788246721709567e-05,
|
| 104 |
+
"loss": 0.7461,
|
| 105 |
+
"step": 500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.24283632831471588,
|
| 109 |
+
"eval_accuracy": 0.697618474861679,
|
| 110 |
+
"eval_f1_macro": 0.6189270686060082,
|
| 111 |
+
"eval_f1_micro": 0.697618474861679,
|
| 112 |
+
"eval_loss": 1.0767923593521118,
|
| 113 |
+
"eval_precision_macro": 0.6453274802012455,
|
| 114 |
+
"eval_precision_micro": 0.697618474861679,
|
| 115 |
+
"eval_recall_macro": 0.6631935550298835,
|
| 116 |
+
"eval_recall_micro": 0.697618474861679,
|
| 117 |
+
"eval_runtime": 77.7991,
|
| 118 |
+
"eval_samples_per_second": 53.433,
|
| 119 |
+
"eval_steps_per_second": 3.342,
|
| 120 |
+
"step": 500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.2914035939776591,
|
| 124 |
+
"grad_norm": 15.981602668762207,
|
| 125 |
+
"learning_rate": 1.8545410393394855e-05,
|
| 126 |
+
"loss": 0.7715,
|
| 127 |
+
"step": 600
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.2914035939776591,
|
| 131 |
+
"eval_accuracy": 0.6793360596584075,
|
| 132 |
+
"eval_f1_macro": 0.6412879956515993,
|
| 133 |
+
"eval_f1_micro": 0.6793360596584075,
|
| 134 |
+
"eval_loss": 1.0772430896759033,
|
| 135 |
+
"eval_precision_macro": 0.6604751299557832,
|
| 136 |
+
"eval_precision_micro": 0.6793360596584075,
|
| 137 |
+
"eval_recall_macro": 0.6882200466749144,
|
| 138 |
+
"eval_recall_micro": 0.6793360596584075,
|
| 139 |
+
"eval_runtime": 78.3813,
|
| 140 |
+
"eval_samples_per_second": 53.036,
|
| 141 |
+
"eval_steps_per_second": 3.317,
|
| 142 |
+
"step": 600
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.33997085964060225,
|
| 146 |
+
"grad_norm": 15.210453033447266,
|
| 147 |
+
"learning_rate": 1.8302574065080135e-05,
|
| 148 |
+
"loss": 0.5764,
|
| 149 |
+
"step": 700
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.33997085964060225,
|
| 153 |
+
"eval_accuracy": 0.7346644214577821,
|
| 154 |
+
"eval_f1_macro": 0.6644040766448638,
|
| 155 |
+
"eval_f1_micro": 0.7346644214577821,
|
| 156 |
+
"eval_loss": 0.9163544178009033,
|
| 157 |
+
"eval_precision_macro": 0.6814907504685033,
|
| 158 |
+
"eval_precision_micro": 0.7346644214577821,
|
| 159 |
+
"eval_recall_macro": 0.7012321944408646,
|
| 160 |
+
"eval_recall_micro": 0.7346644214577821,
|
| 161 |
+
"eval_runtime": 77.9074,
|
| 162 |
+
"eval_samples_per_second": 53.358,
|
| 163 |
+
"eval_steps_per_second": 3.337,
|
| 164 |
+
"step": 700
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3885381253035454,
|
| 168 |
+
"grad_norm": 33.91225051879883,
|
| 169 |
+
"learning_rate": 1.8059737736765423e-05,
|
| 170 |
+
"loss": 0.5638,
|
| 171 |
+
"step": 800
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.3885381253035454,
|
| 175 |
+
"eval_accuracy": 0.7474140004811162,
|
| 176 |
+
"eval_f1_macro": 0.6913277390868877,
|
| 177 |
+
"eval_f1_micro": 0.7474140004811162,
|
| 178 |
+
"eval_loss": 0.889366090297699,
|
| 179 |
+
"eval_precision_macro": 0.7266313115490612,
|
| 180 |
+
"eval_precision_micro": 0.7474140004811162,
|
| 181 |
+
"eval_recall_macro": 0.715908295360388,
|
| 182 |
+
"eval_recall_micro": 0.7474140004811162,
|
| 183 |
+
"eval_runtime": 78.3481,
|
| 184 |
+
"eval_samples_per_second": 53.058,
|
| 185 |
+
"eval_steps_per_second": 3.319,
|
| 186 |
+
"step": 800
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4371053909664886,
|
| 190 |
+
"grad_norm": 8.672567367553711,
|
| 191 |
+
"learning_rate": 1.7816901408450707e-05,
|
| 192 |
+
"loss": 0.5197,
|
| 193 |
+
"step": 900
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.4371053909664886,
|
| 197 |
+
"eval_accuracy": 0.7926389222997354,
|
| 198 |
+
"eval_f1_macro": 0.7247243935175413,
|
| 199 |
+
"eval_f1_micro": 0.7926389222997354,
|
| 200 |
+
"eval_loss": 0.7225074768066406,
|
| 201 |
+
"eval_precision_macro": 0.7255052815535598,
|
| 202 |
+
"eval_precision_micro": 0.7926389222997354,
|
| 203 |
+
"eval_recall_macro": 0.7576197995601733,
|
| 204 |
+
"eval_recall_micro": 0.7926389222997354,
|
| 205 |
+
"eval_runtime": 78.3587,
|
| 206 |
+
"eval_samples_per_second": 53.051,
|
| 207 |
+
"eval_steps_per_second": 3.318,
|
| 208 |
+
"step": 900
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.48567265662943176,
|
| 212 |
+
"grad_norm": 5.37787389755249,
|
| 213 |
+
"learning_rate": 1.757406508013599e-05,
|
| 214 |
+
"loss": 0.4454,
|
| 215 |
+
"step": 1000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.48567265662943176,
|
| 219 |
+
"eval_accuracy": 0.7611258118835699,
|
| 220 |
+
"eval_f1_macro": 0.6918902246005824,
|
| 221 |
+
"eval_f1_micro": 0.7611258118835699,
|
| 222 |
+
"eval_loss": 0.8200820684432983,
|
| 223 |
+
"eval_precision_macro": 0.7248507826718404,
|
| 224 |
+
"eval_precision_micro": 0.7611258118835699,
|
| 225 |
+
"eval_recall_macro": 0.7240661179940105,
|
| 226 |
+
"eval_recall_micro": 0.7611258118835699,
|
| 227 |
+
"eval_runtime": 77.9125,
|
| 228 |
+
"eval_samples_per_second": 53.355,
|
| 229 |
+
"eval_steps_per_second": 3.337,
|
| 230 |
+
"step": 1000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.5342399222923749,
|
| 234 |
+
"grad_norm": 50.15217971801758,
|
| 235 |
+
"learning_rate": 1.7331228751821275e-05,
|
| 236 |
+
"loss": 0.3573,
|
| 237 |
+
"step": 1100
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.5342399222923749,
|
| 241 |
+
"eval_accuracy": 0.7486167909550157,
|
| 242 |
+
"eval_f1_macro": 0.708488926204985,
|
| 243 |
+
"eval_f1_micro": 0.7486167909550158,
|
| 244 |
+
"eval_loss": 0.840596616268158,
|
| 245 |
+
"eval_precision_macro": 0.7458516807418488,
|
| 246 |
+
"eval_precision_micro": 0.7486167909550157,
|
| 247 |
+
"eval_recall_macro": 0.7355897302661839,
|
| 248 |
+
"eval_recall_micro": 0.7486167909550157,
|
| 249 |
+
"eval_runtime": 77.9539,
|
| 250 |
+
"eval_samples_per_second": 53.326,
|
| 251 |
+
"eval_steps_per_second": 3.335,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.5828071879553182,
|
| 256 |
+
"grad_norm": 4.126067161560059,
|
| 257 |
+
"learning_rate": 1.708839242350656e-05,
|
| 258 |
+
"loss": 0.3992,
|
| 259 |
+
"step": 1200
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.5828071879553182,
|
| 263 |
+
"eval_accuracy": 0.7969689680057734,
|
| 264 |
+
"eval_f1_macro": 0.7545628662653078,
|
| 265 |
+
"eval_f1_micro": 0.7969689680057734,
|
| 266 |
+
"eval_loss": 0.7257721424102783,
|
| 267 |
+
"eval_precision_macro": 0.7815422636293521,
|
| 268 |
+
"eval_precision_micro": 0.7969689680057734,
|
| 269 |
+
"eval_recall_macro": 0.76812907504405,
|
| 270 |
+
"eval_recall_micro": 0.7969689680057734,
|
| 271 |
+
"eval_runtime": 78.4205,
|
| 272 |
+
"eval_samples_per_second": 53.009,
|
| 273 |
+
"eval_steps_per_second": 3.315,
|
| 274 |
+
"step": 1200
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.6313744536182613,
|
| 278 |
+
"grad_norm": 9.667169570922852,
|
| 279 |
+
"learning_rate": 1.6845556095191843e-05,
|
| 280 |
+
"loss": 0.3637,
|
| 281 |
+
"step": 1300
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.6313744536182613,
|
| 285 |
+
"eval_accuracy": 0.8181380803464037,
|
| 286 |
+
"eval_f1_macro": 0.7552426483349393,
|
| 287 |
+
"eval_f1_micro": 0.8181380803464037,
|
| 288 |
+
"eval_loss": 0.6487129330635071,
|
| 289 |
+
"eval_precision_macro": 0.770444338655661,
|
| 290 |
+
"eval_precision_micro": 0.8181380803464037,
|
| 291 |
+
"eval_recall_macro": 0.7814605757463501,
|
| 292 |
+
"eval_recall_micro": 0.8181380803464037,
|
| 293 |
+
"eval_runtime": 77.6598,
|
| 294 |
+
"eval_samples_per_second": 53.528,
|
| 295 |
+
"eval_steps_per_second": 3.348,
|
| 296 |
+
"step": 1300
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6799417192812045,
|
| 300 |
+
"grad_norm": 15.598691940307617,
|
| 301 |
+
"learning_rate": 1.6602719766877127e-05,
|
| 302 |
+
"loss": 0.3534,
|
| 303 |
+
"step": 1400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6799417192812045,
|
| 307 |
+
"eval_accuracy": 0.8320904498436372,
|
| 308 |
+
"eval_f1_macro": 0.7756514292421667,
|
| 309 |
+
"eval_f1_micro": 0.8320904498436372,
|
| 310 |
+
"eval_loss": 0.6163076162338257,
|
| 311 |
+
"eval_precision_macro": 0.776765552199579,
|
| 312 |
+
"eval_precision_micro": 0.8320904498436372,
|
| 313 |
+
"eval_recall_macro": 0.807685789299095,
|
| 314 |
+
"eval_recall_micro": 0.8320904498436372,
|
| 315 |
+
"eval_runtime": 78.0973,
|
| 316 |
+
"eval_samples_per_second": 53.228,
|
| 317 |
+
"eval_steps_per_second": 3.329,
|
| 318 |
+
"step": 1400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7285089849441476,
|
| 322 |
+
"grad_norm": 16.200693130493164,
|
| 323 |
+
"learning_rate": 1.635988343856241e-05,
|
| 324 |
+
"loss": 0.2738,
|
| 325 |
+
"step": 1500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7285089849441476,
|
| 329 |
+
"eval_accuracy": 0.8330526822227567,
|
| 330 |
+
"eval_f1_macro": 0.7657709635036466,
|
| 331 |
+
"eval_f1_micro": 0.8330526822227567,
|
| 332 |
+
"eval_loss": 0.5991656184196472,
|
| 333 |
+
"eval_precision_macro": 0.7896026550833485,
|
| 334 |
+
"eval_precision_micro": 0.8330526822227567,
|
| 335 |
+
"eval_recall_macro": 0.7825126366614965,
|
| 336 |
+
"eval_recall_micro": 0.8330526822227567,
|
| 337 |
+
"eval_runtime": 78.1674,
|
| 338 |
+
"eval_samples_per_second": 53.181,
|
| 339 |
+
"eval_steps_per_second": 3.326,
|
| 340 |
+
"step": 1500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.7770762506070908,
|
| 344 |
+
"grad_norm": 22.443140029907227,
|
| 345 |
+
"learning_rate": 1.6117047110247694e-05,
|
| 346 |
+
"loss": 0.2976,
|
| 347 |
+
"step": 1600
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.7770762506070908,
|
| 351 |
+
"eval_accuracy": 0.8277604041375992,
|
| 352 |
+
"eval_f1_macro": 0.7434375371463181,
|
| 353 |
+
"eval_f1_micro": 0.8277604041375993,
|
| 354 |
+
"eval_loss": 0.619115948677063,
|
| 355 |
+
"eval_precision_macro": 0.7596164331235828,
|
| 356 |
+
"eval_precision_micro": 0.8277604041375992,
|
| 357 |
+
"eval_recall_macro": 0.7832912830659067,
|
| 358 |
+
"eval_recall_micro": 0.8277604041375992,
|
| 359 |
+
"eval_runtime": 77.7196,
|
| 360 |
+
"eval_samples_per_second": 53.487,
|
| 361 |
+
"eval_steps_per_second": 3.345,
|
| 362 |
+
"step": 1600
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.825643516270034,
|
| 366 |
+
"grad_norm": 17.786861419677734,
|
| 367 |
+
"learning_rate": 1.587421078193298e-05,
|
| 368 |
+
"loss": 0.2914,
|
| 369 |
+
"step": 1700
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.825643516270034,
|
| 373 |
+
"eval_accuracy": 0.7873466442145778,
|
| 374 |
+
"eval_f1_macro": 0.7264208752916804,
|
| 375 |
+
"eval_f1_micro": 0.7873466442145777,
|
| 376 |
+
"eval_loss": 0.7651363015174866,
|
| 377 |
+
"eval_precision_macro": 0.7408201824968061,
|
| 378 |
+
"eval_precision_micro": 0.7873466442145778,
|
| 379 |
+
"eval_recall_macro": 0.7604117672744211,
|
| 380 |
+
"eval_recall_micro": 0.7873466442145778,
|
| 381 |
+
"eval_runtime": 77.8533,
|
| 382 |
+
"eval_samples_per_second": 53.395,
|
| 383 |
+
"eval_steps_per_second": 3.34,
|
| 384 |
+
"step": 1700
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8742107819329772,
|
| 388 |
+
"grad_norm": 15.827679634094238,
|
| 389 |
+
"learning_rate": 1.5631374453618262e-05,
|
| 390 |
+
"loss": 0.254,
|
| 391 |
+
"step": 1800
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.8742107819329772,
|
| 395 |
+
"eval_accuracy": 0.7729131585277844,
|
| 396 |
+
"eval_f1_macro": 0.7078131643612664,
|
| 397 |
+
"eval_f1_micro": 0.7729131585277844,
|
| 398 |
+
"eval_loss": 0.8441910743713379,
|
| 399 |
+
"eval_precision_macro": 0.7184265914939797,
|
| 400 |
+
"eval_precision_micro": 0.7729131585277844,
|
| 401 |
+
"eval_recall_macro": 0.7567655915669744,
|
| 402 |
+
"eval_recall_micro": 0.7729131585277844,
|
| 403 |
+
"eval_runtime": 78.4035,
|
| 404 |
+
"eval_samples_per_second": 53.021,
|
| 405 |
+
"eval_steps_per_second": 3.316,
|
| 406 |
+
"step": 1800
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.9227780475959203,
|
| 410 |
+
"grad_norm": 13.433658599853516,
|
| 411 |
+
"learning_rate": 1.5388538125303546e-05,
|
| 412 |
+
"loss": 0.2446,
|
| 413 |
+
"step": 1900
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.9227780475959203,
|
| 417 |
+
"eval_accuracy": 0.8330526822227567,
|
| 418 |
+
"eval_f1_macro": 0.7754170140757469,
|
| 419 |
+
"eval_f1_micro": 0.8330526822227567,
|
| 420 |
+
"eval_loss": 0.6231703162193298,
|
| 421 |
+
"eval_precision_macro": 0.7743561402393088,
|
| 422 |
+
"eval_precision_micro": 0.8330526822227567,
|
| 423 |
+
"eval_recall_macro": 0.8166841562149844,
|
| 424 |
+
"eval_recall_micro": 0.8330526822227567,
|
| 425 |
+
"eval_runtime": 77.9333,
|
| 426 |
+
"eval_samples_per_second": 53.341,
|
| 427 |
+
"eval_steps_per_second": 3.336,
|
| 428 |
+
"step": 1900
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.9713453132588635,
|
| 432 |
+
"grad_norm": 1.4447236061096191,
|
| 433 |
+
"learning_rate": 1.514570179698883e-05,
|
| 434 |
+
"loss": 0.2468,
|
| 435 |
+
"step": 2000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.9713453132588635,
|
| 439 |
+
"eval_accuracy": 0.8448400288669714,
|
| 440 |
+
"eval_f1_macro": 0.785930557684152,
|
| 441 |
+
"eval_f1_micro": 0.8448400288669714,
|
| 442 |
+
"eval_loss": 0.5916985869407654,
|
| 443 |
+
"eval_precision_macro": 0.779867107822518,
|
| 444 |
+
"eval_precision_micro": 0.8448400288669714,
|
| 445 |
+
"eval_recall_macro": 0.8258044114789991,
|
| 446 |
+
"eval_recall_micro": 0.8448400288669714,
|
| 447 |
+
"eval_runtime": 78.2704,
|
| 448 |
+
"eval_samples_per_second": 53.111,
|
| 449 |
+
"eval_steps_per_second": 3.322,
|
| 450 |
+
"step": 2000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0199125789218066,
|
| 454 |
+
"grad_norm": 42.209495544433594,
|
| 455 |
+
"learning_rate": 1.4902865468674114e-05,
|
| 456 |
+
"loss": 0.2197,
|
| 457 |
+
"step": 2100
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0199125789218066,
|
| 461 |
+
"eval_accuracy": 0.8210247774837623,
|
| 462 |
+
"eval_f1_macro": 0.7496958773425116,
|
| 463 |
+
"eval_f1_micro": 0.8210247774837625,
|
| 464 |
+
"eval_loss": 0.6304962038993835,
|
| 465 |
+
"eval_precision_macro": 0.7800275333894653,
|
| 466 |
+
"eval_precision_micro": 0.8210247774837623,
|
| 467 |
+
"eval_recall_macro": 0.7725863519296959,
|
| 468 |
+
"eval_recall_micro": 0.8210247774837623,
|
| 469 |
+
"eval_runtime": 78.4172,
|
| 470 |
+
"eval_samples_per_second": 53.011,
|
| 471 |
+
"eval_steps_per_second": 3.316,
|
| 472 |
+
"step": 2100
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0684798445847499,
|
| 476 |
+
"grad_norm": 6.323939800262451,
|
| 477 |
+
"learning_rate": 1.46600291403594e-05,
|
| 478 |
+
"loss": 0.1474,
|
| 479 |
+
"step": 2200
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0684798445847499,
|
| 483 |
+
"eval_accuracy": 0.8210247774837623,
|
| 484 |
+
"eval_f1_macro": 0.7654970298380952,
|
| 485 |
+
"eval_f1_micro": 0.8210247774837625,
|
| 486 |
+
"eval_loss": 0.6584117412567139,
|
| 487 |
+
"eval_precision_macro": 0.7776774908498755,
|
| 488 |
+
"eval_precision_micro": 0.8210247774837623,
|
| 489 |
+
"eval_recall_macro": 0.7832612508206293,
|
| 490 |
+
"eval_recall_micro": 0.8210247774837623,
|
| 491 |
+
"eval_runtime": 78.2294,
|
| 492 |
+
"eval_samples_per_second": 53.139,
|
| 493 |
+
"eval_steps_per_second": 3.324,
|
| 494 |
+
"step": 2200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.117047110247693,
|
| 498 |
+
"grad_norm": 5.200247287750244,
|
| 499 |
+
"learning_rate": 1.4417192812044682e-05,
|
| 500 |
+
"loss": 0.1385,
|
| 501 |
+
"step": 2300
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.117047110247693,
|
| 505 |
+
"eval_accuracy": 0.8465239355304306,
|
| 506 |
+
"eval_f1_macro": 0.795171009913394,
|
| 507 |
+
"eval_f1_micro": 0.8465239355304306,
|
| 508 |
+
"eval_loss": 0.5680557489395142,
|
| 509 |
+
"eval_precision_macro": 0.8036743010238906,
|
| 510 |
+
"eval_precision_micro": 0.8465239355304306,
|
| 511 |
+
"eval_recall_macro": 0.8194950943386284,
|
| 512 |
+
"eval_recall_micro": 0.8465239355304306,
|
| 513 |
+
"eval_runtime": 77.9399,
|
| 514 |
+
"eval_samples_per_second": 53.336,
|
| 515 |
+
"eval_steps_per_second": 3.336,
|
| 516 |
+
"step": 2300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.1656143759106363,
|
| 520 |
+
"grad_norm": 59.158382415771484,
|
| 521 |
+
"learning_rate": 1.4174356483729968e-05,
|
| 522 |
+
"loss": 0.1135,
|
| 523 |
+
"step": 2400
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.1656143759106363,
|
| 527 |
+
"eval_accuracy": 0.867452489776281,
|
| 528 |
+
"eval_f1_macro": 0.8221801724207984,
|
| 529 |
+
"eval_f1_micro": 0.867452489776281,
|
| 530 |
+
"eval_loss": 0.5212485194206238,
|
| 531 |
+
"eval_precision_macro": 0.8331447468612765,
|
| 532 |
+
"eval_precision_micro": 0.867452489776281,
|
| 533 |
+
"eval_recall_macro": 0.8320781071525781,
|
| 534 |
+
"eval_recall_micro": 0.867452489776281,
|
| 535 |
+
"eval_runtime": 78.3816,
|
| 536 |
+
"eval_samples_per_second": 53.035,
|
| 537 |
+
"eval_steps_per_second": 3.317,
|
| 538 |
+
"step": 2400
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.2141816415735793,
|
| 542 |
+
"grad_norm": 1.2092406749725342,
|
| 543 |
+
"learning_rate": 1.393152015541525e-05,
|
| 544 |
+
"loss": 0.153,
|
| 545 |
+
"step": 2500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.2141816415735793,
|
| 549 |
+
"eval_accuracy": 0.854462352658167,
|
| 550 |
+
"eval_f1_macro": 0.79162479913702,
|
| 551 |
+
"eval_f1_micro": 0.854462352658167,
|
| 552 |
+
"eval_loss": 0.5905571579933167,
|
| 553 |
+
"eval_precision_macro": 0.8007086193727224,
|
| 554 |
+
"eval_precision_micro": 0.854462352658167,
|
| 555 |
+
"eval_recall_macro": 0.8240486776141968,
|
| 556 |
+
"eval_recall_micro": 0.854462352658167,
|
| 557 |
+
"eval_runtime": 77.8377,
|
| 558 |
+
"eval_samples_per_second": 53.406,
|
| 559 |
+
"eval_steps_per_second": 3.34,
|
| 560 |
+
"step": 2500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.2627489072365226,
|
| 564 |
+
"grad_norm": 4.295379638671875,
|
| 565 |
+
"learning_rate": 1.3688683827100536e-05,
|
| 566 |
+
"loss": 0.1221,
|
| 567 |
+
"step": 2600
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.2627489072365226,
|
| 571 |
+
"eval_accuracy": 0.8780370459465962,
|
| 572 |
+
"eval_f1_macro": 0.8233792046483023,
|
| 573 |
+
"eval_f1_micro": 0.8780370459465962,
|
| 574 |
+
"eval_loss": 0.48117873072624207,
|
| 575 |
+
"eval_precision_macro": 0.8275579818555562,
|
| 576 |
+
"eval_precision_micro": 0.8780370459465962,
|
| 577 |
+
"eval_recall_macro": 0.8399965589517642,
|
| 578 |
+
"eval_recall_micro": 0.8780370459465962,
|
| 579 |
+
"eval_runtime": 78.2827,
|
| 580 |
+
"eval_samples_per_second": 53.102,
|
| 581 |
+
"eval_steps_per_second": 3.321,
|
| 582 |
+
"step": 2600
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.3113161728994658,
|
| 586 |
+
"grad_norm": 0.7493284940719604,
|
| 587 |
+
"learning_rate": 1.344584749878582e-05,
|
| 588 |
+
"loss": 0.134,
|
| 589 |
+
"step": 2700
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.3113161728994658,
|
| 593 |
+
"eval_accuracy": 0.8525378878999278,
|
| 594 |
+
"eval_f1_macro": 0.8105294018236757,
|
| 595 |
+
"eval_f1_micro": 0.8525378878999278,
|
| 596 |
+
"eval_loss": 0.6301819682121277,
|
| 597 |
+
"eval_precision_macro": 0.8127798645314742,
|
| 598 |
+
"eval_precision_micro": 0.8525378878999278,
|
| 599 |
+
"eval_recall_macro": 0.8407694300980793,
|
| 600 |
+
"eval_recall_micro": 0.8525378878999278,
|
| 601 |
+
"eval_runtime": 78.1792,
|
| 602 |
+
"eval_samples_per_second": 53.173,
|
| 603 |
+
"eval_steps_per_second": 3.326,
|
| 604 |
+
"step": 2700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.359883438562409,
|
| 608 |
+
"grad_norm": 15.269425392150879,
|
| 609 |
+
"learning_rate": 1.3203011170471102e-05,
|
| 610 |
+
"loss": 0.1177,
|
| 611 |
+
"step": 2800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.359883438562409,
|
| 615 |
+
"eval_accuracy": 0.8720230935770988,
|
| 616 |
+
"eval_f1_macro": 0.8162750069957628,
|
| 617 |
+
"eval_f1_micro": 0.872023093577099,
|
| 618 |
+
"eval_loss": 0.5413680672645569,
|
| 619 |
+
"eval_precision_macro": 0.8190184865925261,
|
| 620 |
+
"eval_precision_micro": 0.8720230935770988,
|
| 621 |
+
"eval_recall_macro": 0.8430994278929198,
|
| 622 |
+
"eval_recall_micro": 0.8720230935770988,
|
| 623 |
+
"eval_runtime": 77.9146,
|
| 624 |
+
"eval_samples_per_second": 53.353,
|
| 625 |
+
"eval_steps_per_second": 3.337,
|
| 626 |
+
"step": 2800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.408450704225352,
|
| 630 |
+
"grad_norm": 2.0257482528686523,
|
| 631 |
+
"learning_rate": 1.2960174842156388e-05,
|
| 632 |
+
"loss": 0.0987,
|
| 633 |
+
"step": 2900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.408450704225352,
|
| 637 |
+
"eval_accuracy": 0.8809237430839548,
|
| 638 |
+
"eval_f1_macro": 0.8218294114431427,
|
| 639 |
+
"eval_f1_micro": 0.8809237430839548,
|
| 640 |
+
"eval_loss": 0.5116602182388306,
|
| 641 |
+
"eval_precision_macro": 0.8136201153530077,
|
| 642 |
+
"eval_precision_micro": 0.8809237430839548,
|
| 643 |
+
"eval_recall_macro": 0.8508023667833765,
|
| 644 |
+
"eval_recall_micro": 0.8809237430839548,
|
| 645 |
+
"eval_runtime": 78.002,
|
| 646 |
+
"eval_samples_per_second": 53.294,
|
| 647 |
+
"eval_steps_per_second": 3.333,
|
| 648 |
+
"step": 2900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.4570179698882952,
|
| 652 |
+
"grad_norm": 42.31605529785156,
|
| 653 |
+
"learning_rate": 1.2717338513841673e-05,
|
| 654 |
+
"loss": 0.1058,
|
| 655 |
+
"step": 3000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.4570179698882952,
|
| 659 |
+
"eval_accuracy": 0.8433966802982921,
|
| 660 |
+
"eval_f1_macro": 0.8068375038460742,
|
| 661 |
+
"eval_f1_micro": 0.8433966802982921,
|
| 662 |
+
"eval_loss": 0.6526976823806763,
|
| 663 |
+
"eval_precision_macro": 0.8158791028657807,
|
| 664 |
+
"eval_precision_micro": 0.8433966802982921,
|
| 665 |
+
"eval_recall_macro": 0.8236984397615126,
|
| 666 |
+
"eval_recall_micro": 0.8433966802982921,
|
| 667 |
+
"eval_runtime": 78.2408,
|
| 668 |
+
"eval_samples_per_second": 53.131,
|
| 669 |
+
"eval_steps_per_second": 3.323,
|
| 670 |
+
"step": 3000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.5055852355512385,
|
| 674 |
+
"grad_norm": 0.04906897246837616,
|
| 675 |
+
"learning_rate": 1.2474502185526956e-05,
|
| 676 |
+
"loss": 0.0847,
|
| 677 |
+
"step": 3100
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.5055852355512385,
|
| 681 |
+
"eval_accuracy": 0.8554245850372865,
|
| 682 |
+
"eval_f1_macro": 0.798783246253302,
|
| 683 |
+
"eval_f1_micro": 0.8554245850372865,
|
| 684 |
+
"eval_loss": 0.5800924301147461,
|
| 685 |
+
"eval_precision_macro": 0.8004222933889796,
|
| 686 |
+
"eval_precision_micro": 0.8554245850372865,
|
| 687 |
+
"eval_recall_macro": 0.8243767820708686,
|
| 688 |
+
"eval_recall_micro": 0.8554245850372865,
|
| 689 |
+
"eval_runtime": 77.9481,
|
| 690 |
+
"eval_samples_per_second": 53.33,
|
| 691 |
+
"eval_steps_per_second": 3.336,
|
| 692 |
+
"step": 3100
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.5541525012141817,
|
| 696 |
+
"grad_norm": 0.13342243432998657,
|
| 697 |
+
"learning_rate": 1.223166585721224e-05,
|
| 698 |
+
"loss": 0.0934,
|
| 699 |
+
"step": 3200
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.5541525012141817,
|
| 703 |
+
"eval_accuracy": 0.8433966802982921,
|
| 704 |
+
"eval_f1_macro": 0.7975033136779321,
|
| 705 |
+
"eval_f1_micro": 0.8433966802982921,
|
| 706 |
+
"eval_loss": 0.6552587151527405,
|
| 707 |
+
"eval_precision_macro": 0.7929638472956879,
|
| 708 |
+
"eval_precision_micro": 0.8433966802982921,
|
| 709 |
+
"eval_recall_macro": 0.8272082545582277,
|
| 710 |
+
"eval_recall_micro": 0.8433966802982921,
|
| 711 |
+
"eval_runtime": 78.5124,
|
| 712 |
+
"eval_samples_per_second": 52.947,
|
| 713 |
+
"eval_steps_per_second": 3.312,
|
| 714 |
+
"step": 3200
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.602719766877125,
|
| 718 |
+
"grad_norm": 0.7083119750022888,
|
| 719 |
+
"learning_rate": 1.1988829528897524e-05,
|
| 720 |
+
"loss": 0.0969,
|
| 721 |
+
"step": 3300
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.602719766877125,
|
| 725 |
+
"eval_accuracy": 0.82607649747414,
|
| 726 |
+
"eval_f1_macro": 0.7832101352133586,
|
| 727 |
+
"eval_f1_micro": 0.82607649747414,
|
| 728 |
+
"eval_loss": 0.7666494250297546,
|
| 729 |
+
"eval_precision_macro": 0.7876268324182853,
|
| 730 |
+
"eval_precision_micro": 0.82607649747414,
|
| 731 |
+
"eval_recall_macro": 0.8241865106118899,
|
| 732 |
+
"eval_recall_micro": 0.82607649747414,
|
| 733 |
+
"eval_runtime": 78.311,
|
| 734 |
+
"eval_samples_per_second": 53.083,
|
| 735 |
+
"eval_steps_per_second": 3.32,
|
| 736 |
+
"step": 3300
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.651287032540068,
|
| 740 |
+
"grad_norm": 16.786699295043945,
|
| 741 |
+
"learning_rate": 1.1745993200582808e-05,
|
| 742 |
+
"loss": 0.1428,
|
| 743 |
+
"step": 3400
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.651287032540068,
|
| 747 |
+
"eval_accuracy": 0.8462833774356507,
|
| 748 |
+
"eval_f1_macro": 0.7894688554105801,
|
| 749 |
+
"eval_f1_micro": 0.8462833774356507,
|
| 750 |
+
"eval_loss": 0.685663104057312,
|
| 751 |
+
"eval_precision_macro": 0.7989143890731024,
|
| 752 |
+
"eval_precision_micro": 0.8462833774356507,
|
| 753 |
+
"eval_recall_macro": 0.8135123764257445,
|
| 754 |
+
"eval_recall_micro": 0.8462833774356507,
|
| 755 |
+
"eval_runtime": 78.0482,
|
| 756 |
+
"eval_samples_per_second": 53.262,
|
| 757 |
+
"eval_steps_per_second": 3.331,
|
| 758 |
+
"step": 3400
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.6998542982030111,
|
| 762 |
+
"grad_norm": 27.461700439453125,
|
| 763 |
+
"learning_rate": 1.1503156872268093e-05,
|
| 764 |
+
"loss": 0.0681,
|
| 765 |
+
"step": 3500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.6998542982030111,
|
| 769 |
+
"eval_accuracy": 0.8898243925908107,
|
| 770 |
+
"eval_f1_macro": 0.8280214132166845,
|
| 771 |
+
"eval_f1_micro": 0.8898243925908107,
|
| 772 |
+
"eval_loss": 0.5203650593757629,
|
| 773 |
+
"eval_precision_macro": 0.8341272420720794,
|
| 774 |
+
"eval_precision_micro": 0.8898243925908107,
|
| 775 |
+
"eval_recall_macro": 0.8595091501105108,
|
| 776 |
+
"eval_recall_micro": 0.8898243925908107,
|
| 777 |
+
"eval_runtime": 78.1461,
|
| 778 |
+
"eval_samples_per_second": 53.195,
|
| 779 |
+
"eval_steps_per_second": 3.327,
|
| 780 |
+
"step": 3500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.7484215638659544,
|
| 784 |
+
"grad_norm": 69.4913101196289,
|
| 785 |
+
"learning_rate": 1.1260320543953375e-05,
|
| 786 |
+
"loss": 0.0931,
|
| 787 |
+
"step": 3600
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.7484215638659544,
|
| 791 |
+
"eval_accuracy": 0.8684147221554005,
|
| 792 |
+
"eval_f1_macro": 0.8151692727718802,
|
| 793 |
+
"eval_f1_micro": 0.8684147221554005,
|
| 794 |
+
"eval_loss": 0.6120151281356812,
|
| 795 |
+
"eval_precision_macro": 0.8240793067449873,
|
| 796 |
+
"eval_precision_micro": 0.8684147221554005,
|
| 797 |
+
"eval_recall_macro": 0.8314024627761833,
|
| 798 |
+
"eval_recall_micro": 0.8684147221554005,
|
| 799 |
+
"eval_runtime": 78.1922,
|
| 800 |
+
"eval_samples_per_second": 53.164,
|
| 801 |
+
"eval_steps_per_second": 3.325,
|
| 802 |
+
"step": 3600
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7969888295288974,
|
| 806 |
+
"grad_norm": 0.8026056885719299,
|
| 807 |
+
"learning_rate": 1.1017484215638661e-05,
|
| 808 |
+
"loss": 0.0935,
|
| 809 |
+
"step": 3700
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.7969888295288974,
|
| 813 |
+
"eval_accuracy": 0.8715419773875391,
|
| 814 |
+
"eval_f1_macro": 0.8220476579310915,
|
| 815 |
+
"eval_f1_micro": 0.8715419773875391,
|
| 816 |
+
"eval_loss": 0.5801733732223511,
|
| 817 |
+
"eval_precision_macro": 0.8170628217436031,
|
| 818 |
+
"eval_precision_micro": 0.8715419773875391,
|
| 819 |
+
"eval_recall_macro": 0.8414628001544893,
|
| 820 |
+
"eval_recall_micro": 0.8715419773875391,
|
| 821 |
+
"eval_runtime": 77.92,
|
| 822 |
+
"eval_samples_per_second": 53.35,
|
| 823 |
+
"eval_steps_per_second": 3.337,
|
| 824 |
+
"step": 3700
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.8455560951918408,
|
| 828 |
+
"grad_norm": 20.50851058959961,
|
| 829 |
+
"learning_rate": 1.0774647887323943e-05,
|
| 830 |
+
"loss": 0.1051,
|
| 831 |
+
"step": 3800
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.8455560951918408,
|
| 835 |
+
"eval_accuracy": 0.8638441183545826,
|
| 836 |
+
"eval_f1_macro": 0.8138781743364819,
|
| 837 |
+
"eval_f1_micro": 0.8638441183545826,
|
| 838 |
+
"eval_loss": 0.6387995481491089,
|
| 839 |
+
"eval_precision_macro": 0.8120807002790287,
|
| 840 |
+
"eval_precision_micro": 0.8638441183545826,
|
| 841 |
+
"eval_recall_macro": 0.8384780204857788,
|
| 842 |
+
"eval_recall_micro": 0.8638441183545826,
|
| 843 |
+
"eval_runtime": 78.3578,
|
| 844 |
+
"eval_samples_per_second": 53.052,
|
| 845 |
+
"eval_steps_per_second": 3.318,
|
| 846 |
+
"step": 3800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.8941233608547838,
|
| 850 |
+
"grad_norm": 0.4359864890575409,
|
| 851 |
+
"learning_rate": 1.0531811559009229e-05,
|
| 852 |
+
"loss": 0.1141,
|
| 853 |
+
"step": 3900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.8941233608547838,
|
| 857 |
+
"eval_accuracy": 0.8734664421457782,
|
| 858 |
+
"eval_f1_macro": 0.8181325108037866,
|
| 859 |
+
"eval_f1_micro": 0.8734664421457783,
|
| 860 |
+
"eval_loss": 0.6033037304878235,
|
| 861 |
+
"eval_precision_macro": 0.8257092361144394,
|
| 862 |
+
"eval_precision_micro": 0.8734664421457782,
|
| 863 |
+
"eval_recall_macro": 0.8280682968840635,
|
| 864 |
+
"eval_recall_micro": 0.8734664421457782,
|
| 865 |
+
"eval_runtime": 78.3807,
|
| 866 |
+
"eval_samples_per_second": 53.036,
|
| 867 |
+
"eval_steps_per_second": 3.317,
|
| 868 |
+
"step": 3900
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.942690626517727,
|
| 872 |
+
"grad_norm": 0.026569893583655357,
|
| 873 |
+
"learning_rate": 1.0288975230694513e-05,
|
| 874 |
+
"loss": 0.0782,
|
| 875 |
+
"step": 4000
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.942690626517727,
|
| 879 |
+
"eval_accuracy": 0.8713014192927592,
|
| 880 |
+
"eval_f1_macro": 0.8158890342266224,
|
| 881 |
+
"eval_f1_micro": 0.8713014192927592,
|
| 882 |
+
"eval_loss": 0.6082781553268433,
|
| 883 |
+
"eval_precision_macro": 0.8100721903094688,
|
| 884 |
+
"eval_precision_micro": 0.8713014192927592,
|
| 885 |
+
"eval_recall_macro": 0.8378298843929596,
|
| 886 |
+
"eval_recall_micro": 0.8713014192927592,
|
| 887 |
+
"eval_runtime": 77.7827,
|
| 888 |
+
"eval_samples_per_second": 53.444,
|
| 889 |
+
"eval_steps_per_second": 3.343,
|
| 890 |
+
"step": 4000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.9912578921806703,
|
| 894 |
+
"grad_norm": 0.27337446808815,
|
| 895 |
+
"learning_rate": 1.0046138902379797e-05,
|
| 896 |
+
"loss": 0.0935,
|
| 897 |
+
"step": 4100
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.9912578921806703,
|
| 901 |
+
"eval_accuracy": 0.8385855184026942,
|
| 902 |
+
"eval_f1_macro": 0.7755030296607576,
|
| 903 |
+
"eval_f1_micro": 0.8385855184026941,
|
| 904 |
+
"eval_loss": 0.7882886528968811,
|
| 905 |
+
"eval_precision_macro": 0.772528897611925,
|
| 906 |
+
"eval_precision_micro": 0.8385855184026942,
|
| 907 |
+
"eval_recall_macro": 0.821396700276969,
|
| 908 |
+
"eval_recall_micro": 0.8385855184026942,
|
| 909 |
+
"eval_runtime": 78.0832,
|
| 910 |
+
"eval_samples_per_second": 53.238,
|
| 911 |
+
"eval_steps_per_second": 3.33,
|
| 912 |
+
"step": 4100
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.0398251578436133,
|
| 916 |
+
"grad_norm": 0.06082015484571457,
|
| 917 |
+
"learning_rate": 9.803302574065081e-06,
|
| 918 |
+
"loss": 0.0446,
|
| 919 |
+
"step": 4200
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.0398251578436133,
|
| 923 |
+
"eval_accuracy": 0.8462833774356507,
|
| 924 |
+
"eval_f1_macro": 0.793800305134788,
|
| 925 |
+
"eval_f1_micro": 0.8462833774356507,
|
| 926 |
+
"eval_loss": 0.7242459654808044,
|
| 927 |
+
"eval_precision_macro": 0.8042449609141427,
|
| 928 |
+
"eval_precision_micro": 0.8462833774356507,
|
| 929 |
+
"eval_recall_macro": 0.8070235910631676,
|
| 930 |
+
"eval_recall_micro": 0.8462833774356507,
|
| 931 |
+
"eval_runtime": 78.366,
|
| 932 |
+
"eval_samples_per_second": 53.046,
|
| 933 |
+
"eval_steps_per_second": 3.318,
|
| 934 |
+
"step": 4200
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.0883924235065567,
|
| 938 |
+
"grad_norm": 1.1284111738204956,
|
| 939 |
+
"learning_rate": 9.560466245750365e-06,
|
| 940 |
+
"loss": 0.0394,
|
| 941 |
+
"step": 4300
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.0883924235065567,
|
| 945 |
+
"eval_accuracy": 0.8573490497955256,
|
| 946 |
+
"eval_f1_macro": 0.8097667721853947,
|
| 947 |
+
"eval_f1_micro": 0.8573490497955256,
|
| 948 |
+
"eval_loss": 0.6780639886856079,
|
| 949 |
+
"eval_precision_macro": 0.8206783431890832,
|
| 950 |
+
"eval_precision_micro": 0.8573490497955256,
|
| 951 |
+
"eval_recall_macro": 0.8218729335160754,
|
| 952 |
+
"eval_recall_micro": 0.8573490497955256,
|
| 953 |
+
"eval_runtime": 78.4567,
|
| 954 |
+
"eval_samples_per_second": 52.985,
|
| 955 |
+
"eval_steps_per_second": 3.314,
|
| 956 |
+
"step": 4300
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.1369596891694997,
|
| 960 |
+
"grad_norm": 1.0478459596633911,
|
| 961 |
+
"learning_rate": 9.317629917435649e-06,
|
| 962 |
+
"loss": 0.023,
|
| 963 |
+
"step": 4400
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.1369596891694997,
|
| 967 |
+
"eval_accuracy": 0.8381044022131344,
|
| 968 |
+
"eval_f1_macro": 0.7761721486362632,
|
| 969 |
+
"eval_f1_micro": 0.8381044022131344,
|
| 970 |
+
"eval_loss": 0.8235397934913635,
|
| 971 |
+
"eval_precision_macro": 0.8022053549256318,
|
| 972 |
+
"eval_precision_micro": 0.8381044022131344,
|
| 973 |
+
"eval_recall_macro": 0.8109538575923662,
|
| 974 |
+
"eval_recall_micro": 0.8381044022131344,
|
| 975 |
+
"eval_runtime": 77.944,
|
| 976 |
+
"eval_samples_per_second": 53.333,
|
| 977 |
+
"eval_steps_per_second": 3.336,
|
| 978 |
+
"step": 4400
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1855269548324427,
|
| 982 |
+
"grad_norm": 0.0286689605563879,
|
| 983 |
+
"learning_rate": 9.074793589120935e-06,
|
| 984 |
+
"loss": 0.0338,
|
| 985 |
+
"step": 4500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.1855269548324427,
|
| 989 |
+
"eval_accuracy": 0.8703391869136397,
|
| 990 |
+
"eval_f1_macro": 0.8094122567680977,
|
| 991 |
+
"eval_f1_micro": 0.8703391869136397,
|
| 992 |
+
"eval_loss": 0.6315681338310242,
|
| 993 |
+
"eval_precision_macro": 0.8074299681427781,
|
| 994 |
+
"eval_precision_micro": 0.8703391869136397,
|
| 995 |
+
"eval_recall_macro": 0.8337866144492019,
|
| 996 |
+
"eval_recall_micro": 0.8703391869136397,
|
| 997 |
+
"eval_runtime": 78.3498,
|
| 998 |
+
"eval_samples_per_second": 53.057,
|
| 999 |
+
"eval_steps_per_second": 3.318,
|
| 1000 |
+
"step": 4500
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.234094220495386,
|
| 1004 |
+
"grad_norm": 0.06468763947486877,
|
| 1005 |
+
"learning_rate": 8.831957260806217e-06,
|
| 1006 |
+
"loss": 0.0414,
|
| 1007 |
+
"step": 4600
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.234094220495386,
|
| 1011 |
+
"eval_accuracy": 0.8840509983160934,
|
| 1012 |
+
"eval_f1_macro": 0.824537485440517,
|
| 1013 |
+
"eval_f1_micro": 0.8840509983160935,
|
| 1014 |
+
"eval_loss": 0.5948061347007751,
|
| 1015 |
+
"eval_precision_macro": 0.8233324585853661,
|
| 1016 |
+
"eval_precision_micro": 0.8840509983160934,
|
| 1017 |
+
"eval_recall_macro": 0.8505518969806567,
|
| 1018 |
+
"eval_recall_micro": 0.8840509983160934,
|
| 1019 |
+
"eval_runtime": 77.9733,
|
| 1020 |
+
"eval_samples_per_second": 53.313,
|
| 1021 |
+
"eval_steps_per_second": 3.334,
|
| 1022 |
+
"step": 4600
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.282661486158329,
|
| 1026 |
+
"grad_norm": 4.641617298126221,
|
| 1027 |
+
"learning_rate": 8.5891209324915e-06,
|
| 1028 |
+
"loss": 0.0379,
|
| 1029 |
+
"step": 4700
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.282661486158329,
|
| 1033 |
+
"eval_accuracy": 0.8765936973779168,
|
| 1034 |
+
"eval_f1_macro": 0.825230740105461,
|
| 1035 |
+
"eval_f1_micro": 0.8765936973779168,
|
| 1036 |
+
"eval_loss": 0.5780928134918213,
|
| 1037 |
+
"eval_precision_macro": 0.8206894619069279,
|
| 1038 |
+
"eval_precision_micro": 0.8765936973779168,
|
| 1039 |
+
"eval_recall_macro": 0.841894179116351,
|
| 1040 |
+
"eval_recall_micro": 0.8765936973779168,
|
| 1041 |
+
"eval_runtime": 78.4226,
|
| 1042 |
+
"eval_samples_per_second": 53.008,
|
| 1043 |
+
"eval_steps_per_second": 3.315,
|
| 1044 |
+
"step": 4700
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.3312287518212726,
|
| 1048 |
+
"grad_norm": 0.23332637548446655,
|
| 1049 |
+
"learning_rate": 8.346284604176785e-06,
|
| 1050 |
+
"loss": 0.0473,
|
| 1051 |
+
"step": 4800
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.3312287518212726,
|
| 1055 |
+
"eval_accuracy": 0.8729853259562185,
|
| 1056 |
+
"eval_f1_macro": 0.8052063570572925,
|
| 1057 |
+
"eval_f1_micro": 0.8729853259562185,
|
| 1058 |
+
"eval_loss": 0.6347105503082275,
|
| 1059 |
+
"eval_precision_macro": 0.8294626941554183,
|
| 1060 |
+
"eval_precision_micro": 0.8729853259562185,
|
| 1061 |
+
"eval_recall_macro": 0.8174296733333687,
|
| 1062 |
+
"eval_recall_micro": 0.8729853259562185,
|
| 1063 |
+
"eval_runtime": 77.9725,
|
| 1064 |
+
"eval_samples_per_second": 53.314,
|
| 1065 |
+
"eval_steps_per_second": 3.335,
|
| 1066 |
+
"step": 4800
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.3797960174842157,
|
| 1070 |
+
"grad_norm": 0.014487605541944504,
|
| 1071 |
+
"learning_rate": 8.103448275862069e-06,
|
| 1072 |
+
"loss": 0.0159,
|
| 1073 |
+
"step": 4900
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.3797960174842157,
|
| 1077 |
+
"eval_accuracy": 0.8681741640606206,
|
| 1078 |
+
"eval_f1_macro": 0.8094189525603713,
|
| 1079 |
+
"eval_f1_micro": 0.8681741640606206,
|
| 1080 |
+
"eval_loss": 0.6882294416427612,
|
| 1081 |
+
"eval_precision_macro": 0.8262511053264366,
|
| 1082 |
+
"eval_precision_micro": 0.8681741640606206,
|
| 1083 |
+
"eval_recall_macro": 0.824772348858174,
|
| 1084 |
+
"eval_recall_micro": 0.8681741640606206,
|
| 1085 |
+
"eval_runtime": 78.4876,
|
| 1086 |
+
"eval_samples_per_second": 52.964,
|
| 1087 |
+
"eval_steps_per_second": 3.313,
|
| 1088 |
+
"step": 4900
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.4283632831471587,
|
| 1092 |
+
"grad_norm": 0.011654403060674667,
|
| 1093 |
+
"learning_rate": 7.860611947547354e-06,
|
| 1094 |
+
"loss": 0.0115,
|
| 1095 |
+
"step": 5000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.4283632831471587,
|
| 1099 |
+
"eval_accuracy": 0.8830887659369738,
|
| 1100 |
+
"eval_f1_macro": 0.8288533499086042,
|
| 1101 |
+
"eval_f1_micro": 0.8830887659369738,
|
| 1102 |
+
"eval_loss": 0.5934479832649231,
|
| 1103 |
+
"eval_precision_macro": 0.8396603529798649,
|
| 1104 |
+
"eval_precision_micro": 0.8830887659369738,
|
| 1105 |
+
"eval_recall_macro": 0.8453069551945437,
|
| 1106 |
+
"eval_recall_micro": 0.8830887659369738,
|
| 1107 |
+
"eval_runtime": 78.5682,
|
| 1108 |
+
"eval_samples_per_second": 52.909,
|
| 1109 |
+
"eval_steps_per_second": 3.309,
|
| 1110 |
+
"step": 5000
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.476930548810102,
|
| 1114 |
+
"grad_norm": 21.12113380432129,
|
| 1115 |
+
"learning_rate": 7.617775619232638e-06,
|
| 1116 |
+
"loss": 0.0494,
|
| 1117 |
+
"step": 5100
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.476930548810102,
|
| 1121 |
+
"eval_accuracy": 0.8506134231416888,
|
| 1122 |
+
"eval_f1_macro": 0.7896669170968705,
|
| 1123 |
+
"eval_f1_micro": 0.8506134231416888,
|
| 1124 |
+
"eval_loss": 0.732039749622345,
|
| 1125 |
+
"eval_precision_macro": 0.7898243286153485,
|
| 1126 |
+
"eval_precision_micro": 0.8506134231416888,
|
| 1127 |
+
"eval_recall_macro": 0.8132701383447537,
|
| 1128 |
+
"eval_recall_micro": 0.8506134231416888,
|
| 1129 |
+
"eval_runtime": 78.0419,
|
| 1130 |
+
"eval_samples_per_second": 53.266,
|
| 1131 |
+
"eval_steps_per_second": 3.332,
|
| 1132 |
+
"step": 5100
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.525497814473045,
|
| 1136 |
+
"grad_norm": 0.14766599237918854,
|
| 1137 |
+
"learning_rate": 7.3749392909179215e-06,
|
| 1138 |
+
"loss": 0.0318,
|
| 1139 |
+
"step": 5200
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.525497814473045,
|
| 1143 |
+
"eval_accuracy": 0.8491700745730094,
|
| 1144 |
+
"eval_f1_macro": 0.8013080246715508,
|
| 1145 |
+
"eval_f1_micro": 0.8491700745730094,
|
| 1146 |
+
"eval_loss": 0.775058925151825,
|
| 1147 |
+
"eval_precision_macro": 0.8191511470633912,
|
| 1148 |
+
"eval_precision_micro": 0.8491700745730094,
|
| 1149 |
+
"eval_recall_macro": 0.8104006475463327,
|
| 1150 |
+
"eval_recall_micro": 0.8491700745730094,
|
| 1151 |
+
"eval_runtime": 78.0698,
|
| 1152 |
+
"eval_samples_per_second": 53.247,
|
| 1153 |
+
"eval_steps_per_second": 3.33,
|
| 1154 |
+
"step": 5200
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.5740650801359886,
|
| 1158 |
+
"grad_norm": 0.01593843102455139,
|
| 1159 |
+
"learning_rate": 7.1321029626032054e-06,
|
| 1160 |
+
"loss": 0.0493,
|
| 1161 |
+
"step": 5300
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.5740650801359886,
|
| 1165 |
+
"eval_accuracy": 0.8907866249699302,
|
| 1166 |
+
"eval_f1_macro": 0.846949212010463,
|
| 1167 |
+
"eval_f1_micro": 0.8907866249699302,
|
| 1168 |
+
"eval_loss": 0.5424800515174866,
|
| 1169 |
+
"eval_precision_macro": 0.8565661804143393,
|
| 1170 |
+
"eval_precision_micro": 0.8907866249699302,
|
| 1171 |
+
"eval_recall_macro": 0.852065989778345,
|
| 1172 |
+
"eval_recall_micro": 0.8907866249699302,
|
| 1173 |
+
"eval_runtime": 78.4856,
|
| 1174 |
+
"eval_samples_per_second": 52.965,
|
| 1175 |
+
"eval_steps_per_second": 3.313,
|
| 1176 |
+
"step": 5300
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 2.6226323457989316,
|
| 1180 |
+
"grad_norm": 39.92009353637695,
|
| 1181 |
+
"learning_rate": 6.88926663428849e-06,
|
| 1182 |
+
"loss": 0.0265,
|
| 1183 |
+
"step": 5400
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 2.6226323457989316,
|
| 1187 |
+
"eval_accuracy": 0.8811643011787347,
|
| 1188 |
+
"eval_f1_macro": 0.8343599063711409,
|
| 1189 |
+
"eval_f1_micro": 0.8811643011787347,
|
| 1190 |
+
"eval_loss": 0.5994859933853149,
|
| 1191 |
+
"eval_precision_macro": 0.8496569155300632,
|
| 1192 |
+
"eval_precision_micro": 0.8811643011787347,
|
| 1193 |
+
"eval_recall_macro": 0.8421658331646679,
|
| 1194 |
+
"eval_recall_micro": 0.8811643011787347,
|
| 1195 |
+
"eval_runtime": 78.0929,
|
| 1196 |
+
"eval_samples_per_second": 53.231,
|
| 1197 |
+
"eval_steps_per_second": 3.329,
|
| 1198 |
+
"step": 5400
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.6711996114618746,
|
| 1202 |
+
"grad_norm": 0.05156758427619934,
|
| 1203 |
+
"learning_rate": 6.646430305973774e-06,
|
| 1204 |
+
"loss": 0.0644,
|
| 1205 |
+
"step": 5500
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.6711996114618746,
|
| 1209 |
+
"eval_accuracy": 0.8898243925908107,
|
| 1210 |
+
"eval_f1_macro": 0.8456373260763799,
|
| 1211 |
+
"eval_f1_micro": 0.8898243925908107,
|
| 1212 |
+
"eval_loss": 0.5272171497344971,
|
| 1213 |
+
"eval_precision_macro": 0.8489836763758699,
|
| 1214 |
+
"eval_precision_micro": 0.8898243925908107,
|
| 1215 |
+
"eval_recall_macro": 0.8557074629075649,
|
| 1216 |
+
"eval_recall_micro": 0.8898243925908107,
|
| 1217 |
+
"eval_runtime": 78.4213,
|
| 1218 |
+
"eval_samples_per_second": 53.009,
|
| 1219 |
+
"eval_steps_per_second": 3.315,
|
| 1220 |
+
"step": 5500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.719766877124818,
|
| 1224 |
+
"grad_norm": 0.8775114417076111,
|
| 1225 |
+
"learning_rate": 6.403593977659058e-06,
|
| 1226 |
+
"loss": 0.0452,
|
| 1227 |
+
"step": 5600
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.719766877124818,
|
| 1231 |
+
"eval_accuracy": 0.8650469088284821,
|
| 1232 |
+
"eval_f1_macro": 0.8179080927250358,
|
| 1233 |
+
"eval_f1_micro": 0.8650469088284821,
|
| 1234 |
+
"eval_loss": 0.6951431035995483,
|
| 1235 |
+
"eval_precision_macro": 0.8176656256318844,
|
| 1236 |
+
"eval_precision_micro": 0.8650469088284821,
|
| 1237 |
+
"eval_recall_macro": 0.8412836305297059,
|
| 1238 |
+
"eval_recall_micro": 0.8650469088284821,
|
| 1239 |
+
"eval_runtime": 78.6127,
|
| 1240 |
+
"eval_samples_per_second": 52.879,
|
| 1241 |
+
"eval_steps_per_second": 3.307,
|
| 1242 |
+
"step": 5600
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.768334142787761,
|
| 1246 |
+
"grad_norm": 0.023337820544838905,
|
| 1247 |
+
"learning_rate": 6.160757649344342e-06,
|
| 1248 |
+
"loss": 0.0238,
|
| 1249 |
+
"step": 5700
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.768334142787761,
|
| 1253 |
+
"eval_accuracy": 0.8691363964397402,
|
| 1254 |
+
"eval_f1_macro": 0.8141029552401969,
|
| 1255 |
+
"eval_f1_micro": 0.8691363964397402,
|
| 1256 |
+
"eval_loss": 0.6843555569648743,
|
| 1257 |
+
"eval_precision_macro": 0.828107626781137,
|
| 1258 |
+
"eval_precision_micro": 0.8691363964397402,
|
| 1259 |
+
"eval_recall_macro": 0.8223290635441496,
|
| 1260 |
+
"eval_recall_micro": 0.8691363964397402,
|
| 1261 |
+
"eval_runtime": 77.8775,
|
| 1262 |
+
"eval_samples_per_second": 53.379,
|
| 1263 |
+
"eval_steps_per_second": 3.339,
|
| 1264 |
+
"step": 5700
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.816901408450704,
|
| 1268 |
+
"grad_norm": 2.3684067726135254,
|
| 1269 |
+
"learning_rate": 5.917921321029626e-06,
|
| 1270 |
+
"loss": 0.0344,
|
| 1271 |
+
"step": 5800
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.816901408450704,
|
| 1275 |
+
"eval_accuracy": 0.8842915564108732,
|
| 1276 |
+
"eval_f1_macro": 0.8254107617822057,
|
| 1277 |
+
"eval_f1_micro": 0.8842915564108732,
|
| 1278 |
+
"eval_loss": 0.5869230628013611,
|
| 1279 |
+
"eval_precision_macro": 0.8172320894762466,
|
| 1280 |
+
"eval_precision_micro": 0.8842915564108732,
|
| 1281 |
+
"eval_recall_macro": 0.8495662880335549,
|
| 1282 |
+
"eval_recall_micro": 0.8842915564108732,
|
| 1283 |
+
"eval_runtime": 78.0202,
|
| 1284 |
+
"eval_samples_per_second": 53.281,
|
| 1285 |
+
"eval_steps_per_second": 3.332,
|
| 1286 |
+
"step": 5800
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.8654686741136475,
|
| 1290 |
+
"grad_norm": 0.07361145317554474,
|
| 1291 |
+
"learning_rate": 5.675084992714911e-06,
|
| 1292 |
+
"loss": 0.0212,
|
| 1293 |
+
"step": 5900
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.8654686741136475,
|
| 1297 |
+
"eval_accuracy": 0.8768342554726967,
|
| 1298 |
+
"eval_f1_macro": 0.8234793626505037,
|
| 1299 |
+
"eval_f1_micro": 0.8768342554726967,
|
| 1300 |
+
"eval_loss": 0.6304789185523987,
|
| 1301 |
+
"eval_precision_macro": 0.8184524998357775,
|
| 1302 |
+
"eval_precision_micro": 0.8768342554726967,
|
| 1303 |
+
"eval_recall_macro": 0.8476992326610299,
|
| 1304 |
+
"eval_recall_micro": 0.8768342554726967,
|
| 1305 |
+
"eval_runtime": 78.6516,
|
| 1306 |
+
"eval_samples_per_second": 52.853,
|
| 1307 |
+
"eval_steps_per_second": 3.306,
|
| 1308 |
+
"step": 5900
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.9140359397765905,
|
| 1312 |
+
"grad_norm": 0.009860685095191002,
|
| 1313 |
+
"learning_rate": 5.432248664400195e-06,
|
| 1314 |
+
"loss": 0.0239,
|
| 1315 |
+
"step": 6000
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.9140359397765905,
|
| 1319 |
+
"eval_accuracy": 0.8518162136155881,
|
| 1320 |
+
"eval_f1_macro": 0.8017569225322448,
|
| 1321 |
+
"eval_f1_micro": 0.8518162136155881,
|
| 1322 |
+
"eval_loss": 0.7799412608146667,
|
| 1323 |
+
"eval_precision_macro": 0.7982453929078707,
|
| 1324 |
+
"eval_precision_micro": 0.8518162136155881,
|
| 1325 |
+
"eval_recall_macro": 0.8304382158522342,
|
| 1326 |
+
"eval_recall_micro": 0.8518162136155881,
|
| 1327 |
+
"eval_runtime": 78.0376,
|
| 1328 |
+
"eval_samples_per_second": 53.269,
|
| 1329 |
+
"eval_steps_per_second": 3.332,
|
| 1330 |
+
"step": 6000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 2.9626032054395335,
|
| 1334 |
+
"grad_norm": 0.0258096382021904,
|
| 1335 |
+
"learning_rate": 5.189412336085479e-06,
|
| 1336 |
+
"loss": 0.0293,
|
| 1337 |
+
"step": 6100
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.9626032054395335,
|
| 1341 |
+
"eval_accuracy": 0.8741881164301178,
|
| 1342 |
+
"eval_f1_macro": 0.8230892222950853,
|
| 1343 |
+
"eval_f1_micro": 0.8741881164301178,
|
| 1344 |
+
"eval_loss": 0.6950201392173767,
|
| 1345 |
+
"eval_precision_macro": 0.8197692931333949,
|
| 1346 |
+
"eval_precision_micro": 0.8741881164301178,
|
| 1347 |
+
"eval_recall_macro": 0.8477652020234965,
|
| 1348 |
+
"eval_recall_micro": 0.8741881164301178,
|
| 1349 |
+
"eval_runtime": 78.3208,
|
| 1350 |
+
"eval_samples_per_second": 53.077,
|
| 1351 |
+
"eval_steps_per_second": 3.32,
|
| 1352 |
+
"step": 6100
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.011170471102477,
|
| 1356 |
+
"grad_norm": 0.1370718628168106,
|
| 1357 |
+
"learning_rate": 4.946576007770763e-06,
|
| 1358 |
+
"loss": 0.0288,
|
| 1359 |
+
"step": 6200
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.011170471102477,
|
| 1363 |
+
"eval_accuracy": 0.8789992783257157,
|
| 1364 |
+
"eval_f1_macro": 0.829792442447409,
|
| 1365 |
+
"eval_f1_micro": 0.8789992783257157,
|
| 1366 |
+
"eval_loss": 0.6330971717834473,
|
| 1367 |
+
"eval_precision_macro": 0.8231458659168076,
|
| 1368 |
+
"eval_precision_micro": 0.8789992783257157,
|
| 1369 |
+
"eval_recall_macro": 0.8504144231450652,
|
| 1370 |
+
"eval_recall_micro": 0.8789992783257157,
|
| 1371 |
+
"eval_runtime": 78.7114,
|
| 1372 |
+
"eval_samples_per_second": 52.813,
|
| 1373 |
+
"eval_steps_per_second": 3.303,
|
| 1374 |
+
"step": 6200
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.05973773676542,
|
| 1378 |
+
"grad_norm": 0.055757131427526474,
|
| 1379 |
+
"learning_rate": 4.703739679456047e-06,
|
| 1380 |
+
"loss": 0.0254,
|
| 1381 |
+
"step": 6300
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.05973773676542,
|
| 1385 |
+
"eval_accuracy": 0.8799615107048352,
|
| 1386 |
+
"eval_f1_macro": 0.8318246689081815,
|
| 1387 |
+
"eval_f1_micro": 0.8799615107048352,
|
| 1388 |
+
"eval_loss": 0.63609379529953,
|
| 1389 |
+
"eval_precision_macro": 0.8269628089569904,
|
| 1390 |
+
"eval_precision_micro": 0.8799615107048352,
|
| 1391 |
+
"eval_recall_macro": 0.8565965365714439,
|
| 1392 |
+
"eval_recall_micro": 0.8799615107048352,
|
| 1393 |
+
"eval_runtime": 78.354,
|
| 1394 |
+
"eval_samples_per_second": 53.054,
|
| 1395 |
+
"eval_steps_per_second": 3.318,
|
| 1396 |
+
"step": 6300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.1083050024283634,
|
| 1400 |
+
"grad_norm": 0.006881752982735634,
|
| 1401 |
+
"learning_rate": 4.460903351141332e-06,
|
| 1402 |
+
"loss": 0.0252,
|
| 1403 |
+
"step": 6400
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.1083050024283634,
|
| 1407 |
+
"eval_accuracy": 0.8862160211691124,
|
| 1408 |
+
"eval_f1_macro": 0.8441970931986851,
|
| 1409 |
+
"eval_f1_micro": 0.8862160211691124,
|
| 1410 |
+
"eval_loss": 0.6103322505950928,
|
| 1411 |
+
"eval_precision_macro": 0.8494002256031983,
|
| 1412 |
+
"eval_precision_micro": 0.8862160211691124,
|
| 1413 |
+
"eval_recall_macro": 0.8594469740432842,
|
| 1414 |
+
"eval_recall_micro": 0.8862160211691124,
|
| 1415 |
+
"eval_runtime": 78.3491,
|
| 1416 |
+
"eval_samples_per_second": 53.057,
|
| 1417 |
+
"eval_steps_per_second": 3.318,
|
| 1418 |
+
"step": 6400
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 3.1568722680913064,
|
| 1422 |
+
"grad_norm": 0.02003752812743187,
|
| 1423 |
+
"learning_rate": 4.2180670228266156e-06,
|
| 1424 |
+
"loss": 0.0062,
|
| 1425 |
+
"step": 6500
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 3.1568722680913064,
|
| 1429 |
+
"eval_accuracy": 0.8833293240317537,
|
| 1430 |
+
"eval_f1_macro": 0.8395368491034129,
|
| 1431 |
+
"eval_f1_micro": 0.8833293240317537,
|
| 1432 |
+
"eval_loss": 0.6034556031227112,
|
| 1433 |
+
"eval_precision_macro": 0.8398338415533984,
|
| 1434 |
+
"eval_precision_micro": 0.8833293240317537,
|
| 1435 |
+
"eval_recall_macro": 0.8524929004333107,
|
| 1436 |
+
"eval_recall_micro": 0.8833293240317537,
|
| 1437 |
+
"eval_runtime": 78.6267,
|
| 1438 |
+
"eval_samples_per_second": 52.87,
|
| 1439 |
+
"eval_steps_per_second": 3.307,
|
| 1440 |
+
"step": 6500
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 3.20543953375425,
|
| 1444 |
+
"grad_norm": 0.09360187500715256,
|
| 1445 |
+
"learning_rate": 3.9752306945118995e-06,
|
| 1446 |
+
"loss": 0.0176,
|
| 1447 |
+
"step": 6600
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 3.20543953375425,
|
| 1451 |
+
"eval_accuracy": 0.8850132306952129,
|
| 1452 |
+
"eval_f1_macro": 0.8304379003006633,
|
| 1453 |
+
"eval_f1_micro": 0.8850132306952128,
|
| 1454 |
+
"eval_loss": 0.6116442084312439,
|
| 1455 |
+
"eval_precision_macro": 0.8326738669282544,
|
| 1456 |
+
"eval_precision_micro": 0.8850132306952129,
|
| 1457 |
+
"eval_recall_macro": 0.85264914984025,
|
| 1458 |
+
"eval_recall_micro": 0.8850132306952129,
|
| 1459 |
+
"eval_runtime": 78.4069,
|
| 1460 |
+
"eval_samples_per_second": 53.018,
|
| 1461 |
+
"eval_steps_per_second": 3.316,
|
| 1462 |
+
"step": 6600
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 3.254006799417193,
|
| 1466 |
+
"grad_norm": 0.0037081497721374035,
|
| 1467 |
+
"learning_rate": 3.7323943661971835e-06,
|
| 1468 |
+
"loss": 0.0077,
|
| 1469 |
+
"step": 6700
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 3.254006799417193,
|
| 1473 |
+
"eval_accuracy": 0.8845321145056532,
|
| 1474 |
+
"eval_f1_macro": 0.8347831431371906,
|
| 1475 |
+
"eval_f1_micro": 0.8845321145056532,
|
| 1476 |
+
"eval_loss": 0.6256404519081116,
|
| 1477 |
+
"eval_precision_macro": 0.8436031947040645,
|
| 1478 |
+
"eval_precision_micro": 0.8845321145056532,
|
| 1479 |
+
"eval_recall_macro": 0.8486489503127234,
|
| 1480 |
+
"eval_recall_micro": 0.8845321145056532,
|
| 1481 |
+
"eval_runtime": 78.5317,
|
| 1482 |
+
"eval_samples_per_second": 52.934,
|
| 1483 |
+
"eval_steps_per_second": 3.311,
|
| 1484 |
+
"step": 6700
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 3.302574065080136,
|
| 1488 |
+
"grad_norm": 0.06124697998166084,
|
| 1489 |
+
"learning_rate": 3.4895580378824675e-06,
|
| 1490 |
+
"loss": 0.0127,
|
| 1491 |
+
"step": 6800
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 3.302574065080136,
|
| 1495 |
+
"eval_accuracy": 0.8794803945152755,
|
| 1496 |
+
"eval_f1_macro": 0.8278216288594707,
|
| 1497 |
+
"eval_f1_micro": 0.8794803945152755,
|
| 1498 |
+
"eval_loss": 0.6568040251731873,
|
| 1499 |
+
"eval_precision_macro": 0.8467736273399344,
|
| 1500 |
+
"eval_precision_micro": 0.8794803945152755,
|
| 1501 |
+
"eval_recall_macro": 0.8387083670261228,
|
| 1502 |
+
"eval_recall_micro": 0.8794803945152755,
|
| 1503 |
+
"eval_runtime": 78.3608,
|
| 1504 |
+
"eval_samples_per_second": 53.05,
|
| 1505 |
+
"eval_steps_per_second": 3.318,
|
| 1506 |
+
"step": 6800
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 3.3511413307430793,
|
| 1510 |
+
"grad_norm": 0.25665995478630066,
|
| 1511 |
+
"learning_rate": 3.246721709567752e-06,
|
| 1512 |
+
"loss": 0.0178,
|
| 1513 |
+
"step": 6900
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 3.3511413307430793,
|
| 1517 |
+
"eval_accuracy": 0.8713014192927592,
|
| 1518 |
+
"eval_f1_macro": 0.8179505523753748,
|
| 1519 |
+
"eval_f1_micro": 0.8713014192927592,
|
| 1520 |
+
"eval_loss": 0.7154167890548706,
|
| 1521 |
+
"eval_precision_macro": 0.8310341284957633,
|
| 1522 |
+
"eval_precision_micro": 0.8713014192927592,
|
| 1523 |
+
"eval_recall_macro": 0.8341873689934125,
|
| 1524 |
+
"eval_recall_micro": 0.8713014192927592,
|
| 1525 |
+
"eval_runtime": 78.685,
|
| 1526 |
+
"eval_samples_per_second": 52.831,
|
| 1527 |
+
"eval_steps_per_second": 3.304,
|
| 1528 |
+
"step": 6900
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.3997085964060223,
|
| 1532 |
+
"grad_norm": 0.037899695336818695,
|
| 1533 |
+
"learning_rate": 3.0038853812530354e-06,
|
| 1534 |
+
"loss": 0.0019,
|
| 1535 |
+
"step": 7000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.3997085964060223,
|
| 1539 |
+
"eval_accuracy": 0.8816454173682945,
|
| 1540 |
+
"eval_f1_macro": 0.833404594848917,
|
| 1541 |
+
"eval_f1_micro": 0.8816454173682945,
|
| 1542 |
+
"eval_loss": 0.6380771994590759,
|
| 1543 |
+
"eval_precision_macro": 0.8392890539432627,
|
| 1544 |
+
"eval_precision_micro": 0.8816454173682945,
|
| 1545 |
+
"eval_recall_macro": 0.8437175960246225,
|
| 1546 |
+
"eval_recall_micro": 0.8816454173682945,
|
| 1547 |
+
"eval_runtime": 78.6949,
|
| 1548 |
+
"eval_samples_per_second": 52.824,
|
| 1549 |
+
"eval_steps_per_second": 3.304,
|
| 1550 |
+
"step": 7000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.4482758620689653,
|
| 1554 |
+
"grad_norm": 31.638689041137695,
|
| 1555 |
+
"learning_rate": 2.7610490529383198e-06,
|
| 1556 |
+
"loss": 0.0142,
|
| 1557 |
+
"step": 7100
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.4482758620689653,
|
| 1561 |
+
"eval_accuracy": 0.8828482078421939,
|
| 1562 |
+
"eval_f1_macro": 0.833083270199735,
|
| 1563 |
+
"eval_f1_micro": 0.8828482078421939,
|
| 1564 |
+
"eval_loss": 0.6579678058624268,
|
| 1565 |
+
"eval_precision_macro": 0.8455418017703596,
|
| 1566 |
+
"eval_precision_micro": 0.8828482078421939,
|
| 1567 |
+
"eval_recall_macro": 0.8454918923836,
|
| 1568 |
+
"eval_recall_micro": 0.8828482078421939,
|
| 1569 |
+
"eval_runtime": 78.211,
|
| 1570 |
+
"eval_samples_per_second": 53.151,
|
| 1571 |
+
"eval_steps_per_second": 3.324,
|
| 1572 |
+
"step": 7100
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 3.4968431277319088,
|
| 1576 |
+
"grad_norm": 28.2841796875,
|
| 1577 |
+
"learning_rate": 2.5182127246236037e-06,
|
| 1578 |
+
"loss": 0.0018,
|
| 1579 |
+
"step": 7200
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 3.4968431277319088,
|
| 1583 |
+
"eval_accuracy": 0.8746692326196777,
|
| 1584 |
+
"eval_f1_macro": 0.8263362849592439,
|
| 1585 |
+
"eval_f1_micro": 0.8746692326196777,
|
| 1586 |
+
"eval_loss": 0.6722654104232788,
|
| 1587 |
+
"eval_precision_macro": 0.8233328721924625,
|
| 1588 |
+
"eval_precision_micro": 0.8746692326196777,
|
| 1589 |
+
"eval_recall_macro": 0.8458647636918942,
|
| 1590 |
+
"eval_recall_micro": 0.8746692326196777,
|
| 1591 |
+
"eval_runtime": 78.2301,
|
| 1592 |
+
"eval_samples_per_second": 53.138,
|
| 1593 |
+
"eval_steps_per_second": 3.324,
|
| 1594 |
+
"step": 7200
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 3.5454103933948518,
|
| 1598 |
+
"grad_norm": 0.006923174951225519,
|
| 1599 |
+
"learning_rate": 2.2753763963088877e-06,
|
| 1600 |
+
"loss": 0.0159,
|
| 1601 |
+
"step": 7300
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 3.5454103933948518,
|
| 1605 |
+
"eval_accuracy": 0.8700986288188598,
|
| 1606 |
+
"eval_f1_macro": 0.8196568446600343,
|
| 1607 |
+
"eval_f1_micro": 0.8700986288188598,
|
| 1608 |
+
"eval_loss": 0.7045225501060486,
|
| 1609 |
+
"eval_precision_macro": 0.8167725390706483,
|
| 1610 |
+
"eval_precision_micro": 0.8700986288188598,
|
| 1611 |
+
"eval_recall_macro": 0.8395234839263153,
|
| 1612 |
+
"eval_recall_micro": 0.8700986288188598,
|
| 1613 |
+
"eval_runtime": 78.7461,
|
| 1614 |
+
"eval_samples_per_second": 52.79,
|
| 1615 |
+
"eval_steps_per_second": 3.302,
|
| 1616 |
+
"step": 7300
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 3.593977659057795,
|
| 1620 |
+
"grad_norm": 0.011453253217041492,
|
| 1621 |
+
"learning_rate": 2.032540067994172e-06,
|
| 1622 |
+
"loss": 0.0037,
|
| 1623 |
+
"step": 7400
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 3.593977659057795,
|
| 1627 |
+
"eval_accuracy": 0.882607649747414,
|
| 1628 |
+
"eval_f1_macro": 0.8337455736704167,
|
| 1629 |
+
"eval_f1_micro": 0.882607649747414,
|
| 1630 |
+
"eval_loss": 0.6420170068740845,
|
| 1631 |
+
"eval_precision_macro": 0.8351021322092593,
|
| 1632 |
+
"eval_precision_micro": 0.882607649747414,
|
| 1633 |
+
"eval_recall_macro": 0.8453310977676587,
|
| 1634 |
+
"eval_recall_micro": 0.882607649747414,
|
| 1635 |
+
"eval_runtime": 78.3451,
|
| 1636 |
+
"eval_samples_per_second": 53.06,
|
| 1637 |
+
"eval_steps_per_second": 3.319,
|
| 1638 |
+
"step": 7400
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 3.642544924720738,
|
| 1642 |
+
"grad_norm": 0.004663607105612755,
|
| 1643 |
+
"learning_rate": 1.789703739679456e-06,
|
| 1644 |
+
"loss": 0.0084,
|
| 1645 |
+
"step": 7500
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 3.642544924720738,
|
| 1649 |
+
"eval_accuracy": 0.8802020687996152,
|
| 1650 |
+
"eval_f1_macro": 0.8320621801285876,
|
| 1651 |
+
"eval_f1_micro": 0.8802020687996152,
|
| 1652 |
+
"eval_loss": 0.652312695980072,
|
| 1653 |
+
"eval_precision_macro": 0.8306346210019144,
|
| 1654 |
+
"eval_precision_micro": 0.8802020687996152,
|
| 1655 |
+
"eval_recall_macro": 0.8493781023440272,
|
| 1656 |
+
"eval_recall_micro": 0.8802020687996152,
|
| 1657 |
+
"eval_runtime": 78.7968,
|
| 1658 |
+
"eval_samples_per_second": 52.756,
|
| 1659 |
+
"eval_steps_per_second": 3.3,
|
| 1660 |
+
"step": 7500
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 3.6911121903836817,
|
| 1664 |
+
"grad_norm": 0.05554908514022827,
|
| 1665 |
+
"learning_rate": 1.5468674113647402e-06,
|
| 1666 |
+
"loss": 0.0017,
|
| 1667 |
+
"step": 7600
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 3.6911121903836817,
|
| 1671 |
+
"eval_accuracy": 0.8874188116430118,
|
| 1672 |
+
"eval_f1_macro": 0.8401905388217382,
|
| 1673 |
+
"eval_f1_micro": 0.8874188116430118,
|
| 1674 |
+
"eval_loss": 0.6221657395362854,
|
| 1675 |
+
"eval_precision_macro": 0.8387107750272869,
|
| 1676 |
+
"eval_precision_micro": 0.8874188116430118,
|
| 1677 |
+
"eval_recall_macro": 0.8610361407962509,
|
| 1678 |
+
"eval_recall_micro": 0.8874188116430118,
|
| 1679 |
+
"eval_runtime": 78.6101,
|
| 1680 |
+
"eval_samples_per_second": 52.881,
|
| 1681 |
+
"eval_steps_per_second": 3.307,
|
| 1682 |
+
"step": 7600
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.7396794560466247,
|
| 1686 |
+
"grad_norm": 2.2692418098449707,
|
| 1687 |
+
"learning_rate": 1.3040310830500244e-06,
|
| 1688 |
+
"loss": 0.0071,
|
| 1689 |
+
"step": 7700
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 3.7396794560466247,
|
| 1693 |
+
"eval_accuracy": 0.8785181621361559,
|
| 1694 |
+
"eval_f1_macro": 0.8326744354650085,
|
| 1695 |
+
"eval_f1_micro": 0.878518162136156,
|
| 1696 |
+
"eval_loss": 0.664691686630249,
|
| 1697 |
+
"eval_precision_macro": 0.8341535564737329,
|
| 1698 |
+
"eval_precision_micro": 0.8785181621361559,
|
| 1699 |
+
"eval_recall_macro": 0.8463902152998535,
|
| 1700 |
+
"eval_recall_micro": 0.8785181621361559,
|
| 1701 |
+
"eval_runtime": 78.4331,
|
| 1702 |
+
"eval_samples_per_second": 53.001,
|
| 1703 |
+
"eval_steps_per_second": 3.315,
|
| 1704 |
+
"step": 7700
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.7882467217095677,
|
| 1708 |
+
"grad_norm": 0.009112412109971046,
|
| 1709 |
+
"learning_rate": 1.0611947547353086e-06,
|
| 1710 |
+
"loss": 0.0018,
|
| 1711 |
+
"step": 7800
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 3.7882467217095677,
|
| 1715 |
+
"eval_accuracy": 0.8787587202309358,
|
| 1716 |
+
"eval_f1_macro": 0.8287278332969615,
|
| 1717 |
+
"eval_f1_micro": 0.8787587202309358,
|
| 1718 |
+
"eval_loss": 0.6747535467147827,
|
| 1719 |
+
"eval_precision_macro": 0.8265516787617085,
|
| 1720 |
+
"eval_precision_micro": 0.8787587202309358,
|
| 1721 |
+
"eval_recall_macro": 0.8490595593522744,
|
| 1722 |
+
"eval_recall_micro": 0.8787587202309358,
|
| 1723 |
+
"eval_runtime": 78.5872,
|
| 1724 |
+
"eval_samples_per_second": 52.897,
|
| 1725 |
+
"eval_steps_per_second": 3.308,
|
| 1726 |
+
"step": 7800
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 3.836813987372511,
|
| 1730 |
+
"grad_norm": 0.08465871959924698,
|
| 1731 |
+
"learning_rate": 8.183584264205927e-07,
|
| 1732 |
+
"loss": 0.0063,
|
| 1733 |
+
"step": 7900
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 3.836813987372511,
|
| 1737 |
+
"eval_accuracy": 0.8802020687996152,
|
| 1738 |
+
"eval_f1_macro": 0.8275737635437894,
|
| 1739 |
+
"eval_f1_micro": 0.8802020687996152,
|
| 1740 |
+
"eval_loss": 0.6518697142601013,
|
| 1741 |
+
"eval_precision_macro": 0.8241036586009164,
|
| 1742 |
+
"eval_precision_micro": 0.8802020687996152,
|
| 1743 |
+
"eval_recall_macro": 0.8505984084112971,
|
| 1744 |
+
"eval_recall_micro": 0.8802020687996152,
|
| 1745 |
+
"eval_runtime": 78.3552,
|
| 1746 |
+
"eval_samples_per_second": 53.053,
|
| 1747 |
+
"eval_steps_per_second": 3.318,
|
| 1748 |
+
"step": 7900
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 3.885381253035454,
|
| 1752 |
+
"grad_norm": 0.01252959668636322,
|
| 1753 |
+
"learning_rate": 5.755220981058767e-07,
|
| 1754 |
+
"loss": 0.0012,
|
| 1755 |
+
"step": 8000
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 3.885381253035454,
|
| 1759 |
+
"eval_accuracy": 0.8816454173682945,
|
| 1760 |
+
"eval_f1_macro": 0.8325617260526238,
|
| 1761 |
+
"eval_f1_micro": 0.8816454173682945,
|
| 1762 |
+
"eval_loss": 0.6509329080581665,
|
| 1763 |
+
"eval_precision_macro": 0.8261296227157098,
|
| 1764 |
+
"eval_precision_micro": 0.8816454173682945,
|
| 1765 |
+
"eval_recall_macro": 0.8554119401439346,
|
| 1766 |
+
"eval_recall_micro": 0.8816454173682945,
|
| 1767 |
+
"eval_runtime": 78.6734,
|
| 1768 |
+
"eval_samples_per_second": 52.839,
|
| 1769 |
+
"eval_steps_per_second": 3.305,
|
| 1770 |
+
"step": 8000
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 3.933948518698397,
|
| 1774 |
+
"grad_norm": 0.00854838639497757,
|
| 1775 |
+
"learning_rate": 3.3268576979116075e-07,
|
| 1776 |
+
"loss": 0.0062,
|
| 1777 |
+
"step": 8100
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 3.933948518698397,
|
| 1781 |
+
"eval_accuracy": 0.8811643011787347,
|
| 1782 |
+
"eval_f1_macro": 0.8331789648254515,
|
| 1783 |
+
"eval_f1_micro": 0.8811643011787347,
|
| 1784 |
+
"eval_loss": 0.6525153517723083,
|
| 1785 |
+
"eval_precision_macro": 0.8280847186790202,
|
| 1786 |
+
"eval_precision_micro": 0.8811643011787347,
|
| 1787 |
+
"eval_recall_macro": 0.8554521062472861,
|
| 1788 |
+
"eval_recall_micro": 0.8811643011787347,
|
| 1789 |
+
"eval_runtime": 78.2235,
|
| 1790 |
+
"eval_samples_per_second": 53.143,
|
| 1791 |
+
"eval_steps_per_second": 3.324,
|
| 1792 |
+
"step": 8100
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 3.9825157843613406,
|
| 1796 |
+
"grad_norm": 0.004602006636559963,
|
| 1797 |
+
"learning_rate": 8.984944147644487e-08,
|
| 1798 |
+
"loss": 0.0097,
|
| 1799 |
+
"step": 8200
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 3.9825157843613406,
|
| 1803 |
+
"eval_accuracy": 0.8802020687996152,
|
| 1804 |
+
"eval_f1_macro": 0.832469524971897,
|
| 1805 |
+
"eval_f1_micro": 0.8802020687996152,
|
| 1806 |
+
"eval_loss": 0.6588266491889954,
|
| 1807 |
+
"eval_precision_macro": 0.8274534781731434,
|
| 1808 |
+
"eval_precision_micro": 0.8802020687996152,
|
| 1809 |
+
"eval_recall_macro": 0.8546630804582604,
|
| 1810 |
+
"eval_recall_micro": 0.8802020687996152,
|
| 1811 |
+
"eval_runtime": 78.8748,
|
| 1812 |
+
"eval_samples_per_second": 52.704,
|
| 1813 |
+
"eval_steps_per_second": 3.296,
|
| 1814 |
+
"step": 8200
|
| 1815 |
+
}
|
| 1816 |
+
],
|
| 1817 |
+
"logging_steps": 100,
|
| 1818 |
+
"max_steps": 8236,
|
| 1819 |
+
"num_input_tokens_seen": 0,
|
| 1820 |
+
"num_train_epochs": 4,
|
| 1821 |
+
"save_steps": 100,
|
| 1822 |
+
"stateful_callbacks": {
|
| 1823 |
+
"TrainerControl": {
|
| 1824 |
+
"args": {
|
| 1825 |
+
"should_epoch_stop": false,
|
| 1826 |
+
"should_evaluate": false,
|
| 1827 |
+
"should_log": false,
|
| 1828 |
+
"should_save": true,
|
| 1829 |
+
"should_training_stop": true
|
| 1830 |
+
},
|
| 1831 |
+
"attributes": {}
|
| 1832 |
+
}
|
| 1833 |
+
},
|
| 1834 |
+
"total_flos": 3.467447932454093e+16,
|
| 1835 |
+
"train_batch_size": 16,
|
| 1836 |
+
"trial_name": null,
|
| 1837 |
+
"trial_params": null
|
| 1838 |
+
}
|
checkpoint-8236/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81185f838ff4005f143cdc05247881e3041d333be8afba1fe331ee011795371e
|
| 3 |
+
size 5304
|
checkpoint-8236/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_10": 10,
|
| 40 |
+
"LABEL_11": 11,
|
| 41 |
+
"LABEL_12": 12,
|
| 42 |
+
"LABEL_13": 13,
|
| 43 |
+
"LABEL_14": 14,
|
| 44 |
+
"LABEL_15": 15,
|
| 45 |
+
"LABEL_16": 16,
|
| 46 |
+
"LABEL_17": 17,
|
| 47 |
+
"LABEL_18": 18,
|
| 48 |
+
"LABEL_19": 19,
|
| 49 |
+
"LABEL_2": 2,
|
| 50 |
+
"LABEL_20": 20,
|
| 51 |
+
"LABEL_3": 3,
|
| 52 |
+
"LABEL_4": 4,
|
| 53 |
+
"LABEL_5": 5,
|
| 54 |
+
"LABEL_6": 6,
|
| 55 |
+
"LABEL_7": 7,
|
| 56 |
+
"LABEL_8": 8,
|
| 57 |
+
"LABEL_9": 9
|
| 58 |
+
},
|
| 59 |
+
"layer_norm_eps": 1e-12,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"model_type": "bert",
|
| 62 |
+
"num_attention_heads": 12,
|
| 63 |
+
"num_hidden_layers": 12,
|
| 64 |
+
"pad_token_id": 0,
|
| 65 |
+
"position_embedding_type": "absolute",
|
| 66 |
+
"problem_type": "single_label_classification",
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.52.4",
|
| 69 |
+
"type_vocab_size": 2,
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 30000
|
| 72 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6377d16c4d7efc62c1157e3da9237b2bcab325b3b1ce7725332f9ccbd626f5c
|
| 3 |
+
size 436413500
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81185f838ff4005f143cdc05247881e3041d333be8afba1fe331ee011795371e
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|