Training in progress, step 2500
Browse files- model.safetensors +1 -1
- run-4/checkpoint-2000/config.json +48 -0
- run-4/checkpoint-2000/model.safetensors +3 -0
- run-4/checkpoint-2000/optimizer.pt +3 -0
- run-4/checkpoint-2000/rng_state.pth +3 -0
- run-4/checkpoint-2000/scheduler.pt +3 -0
- run-4/checkpoint-2000/special_tokens_map.json +51 -0
- run-4/checkpoint-2000/tokenizer.json +0 -0
- run-4/checkpoint-2000/tokenizer_config.json +59 -0
- run-4/checkpoint-2000/trainer_state.json +626 -0
- run-4/checkpoint-2000/training_args.bin +3 -0
- run-4/checkpoint-2000/vocab.txt +0 -0
- run-4/checkpoint-2500/config.json +48 -0
- run-4/checkpoint-2500/model.safetensors +3 -0
- run-4/checkpoint-2500/optimizer.pt +3 -0
- run-4/checkpoint-2500/rng_state.pth +3 -0
- run-4/checkpoint-2500/scheduler.pt +3 -0
- run-4/checkpoint-2500/special_tokens_map.json +51 -0
- run-4/checkpoint-2500/tokenizer.json +0 -0
- run-4/checkpoint-2500/tokenizer_config.json +59 -0
- run-4/checkpoint-2500/trainer_state.json +776 -0
- run-4/checkpoint-2500/training_args.bin +3 -0
- run-4/checkpoint-2500/vocab.txt +0 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442518124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6461af843c6c7333946db134fe7890d35e1dfc639af13611c714f9d8aa47db25
|
| 3 |
size 442518124
|
run-4/checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5,
|
| 32 |
+
"LABEL_6": 6
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"max_position_embeddings": 514,
|
| 36 |
+
"model_type": "roberta",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "single_label_classification",
|
| 42 |
+
"tokenizer_class": "BertTokenizer",
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.37.0",
|
| 45 |
+
"type_vocab_size": 1,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 32000
|
| 48 |
+
}
|
run-4/checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7917a1de1d02a74e9ea72f8a7a1505f2a6b9b7f822ae94f8acfee4509a27614
|
| 3 |
+
size 442518124
|
run-4/checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:723f31ca1ccdad6029fe602c2e34b4feb3f54ed118b6fa23b937f2323760c736
|
| 3 |
+
size 885156090
|
run-4/checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdec933332953cfffd8955c5617533e24c3283152b499ae2e782297024da44e7
|
| 3 |
+
size 14244
|
run-4/checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e22c87ffd8381adf1da9dffdd449de9a6981899a4178539f8ddcb3583dbdcfbb
|
| 3 |
+
size 1064
|
run-4/checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
run-4/checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-4/checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 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 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 512,
|
| 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 |
+
}
|
run-4/checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,626 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8332197609307695,
|
| 3 |
+
"best_model_checkpoint": "test-klue/ynat/run-4/checkpoint-1500",
|
| 4 |
+
"epoch": 1.7513134851138354,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 9.563310020185664e-06,
|
| 14 |
+
"loss": 1.9366,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"eval_f1": 0.03217818600688812,
|
| 20 |
+
"eval_loss": 2.097200393676758,
|
| 21 |
+
"eval_runtime": 12.873,
|
| 22 |
+
"eval_samples_per_second": 707.45,
|
| 23 |
+
"eval_steps_per_second": 1.398,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09,
|
| 28 |
+
"learning_rate": 9.421673319649739e-06,
|
| 29 |
+
"loss": 1.7978,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09,
|
| 34 |
+
"eval_f1": 0.5091097821827345,
|
| 35 |
+
"eval_loss": 1.6588668823242188,
|
| 36 |
+
"eval_runtime": 13.4227,
|
| 37 |
+
"eval_samples_per_second": 678.477,
|
| 38 |
+
"eval_steps_per_second": 1.341,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 9.280036619113814e-06,
|
| 44 |
+
"loss": 1.021,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13,
|
| 49 |
+
"eval_f1": 0.6592011581290811,
|
| 50 |
+
"eval_loss": 1.1230525970458984,
|
| 51 |
+
"eval_runtime": 13.0831,
|
| 52 |
+
"eval_samples_per_second": 696.09,
|
| 53 |
+
"eval_steps_per_second": 1.376,
|
| 54 |
+
"step": 150
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.18,
|
| 58 |
+
"learning_rate": 9.13839991857789e-06,
|
| 59 |
+
"loss": 0.7302,
|
| 60 |
+
"step": 200
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.18,
|
| 64 |
+
"eval_f1": 0.627432664776629,
|
| 65 |
+
"eval_loss": 1.1058144569396973,
|
| 66 |
+
"eval_runtime": 12.7078,
|
| 67 |
+
"eval_samples_per_second": 716.644,
|
| 68 |
+
"eval_steps_per_second": 1.416,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.22,
|
| 73 |
+
"learning_rate": 8.996763218041963e-06,
|
| 74 |
+
"loss": 0.6429,
|
| 75 |
+
"step": 250
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.22,
|
| 79 |
+
"eval_f1": 0.734522756164717,
|
| 80 |
+
"eval_loss": 0.8953863382339478,
|
| 81 |
+
"eval_runtime": 12.6114,
|
| 82 |
+
"eval_samples_per_second": 722.125,
|
| 83 |
+
"eval_steps_per_second": 1.427,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.26,
|
| 88 |
+
"learning_rate": 8.855126517506038e-06,
|
| 89 |
+
"loss": 0.6025,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.26,
|
| 94 |
+
"eval_f1": 0.7221910843221135,
|
| 95 |
+
"eval_loss": 0.8775734305381775,
|
| 96 |
+
"eval_runtime": 12.7554,
|
| 97 |
+
"eval_samples_per_second": 713.971,
|
| 98 |
+
"eval_steps_per_second": 1.411,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.31,
|
| 103 |
+
"learning_rate": 8.713489816970114e-06,
|
| 104 |
+
"loss": 0.6414,
|
| 105 |
+
"step": 350
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.31,
|
| 109 |
+
"eval_f1": 0.7759207244222568,
|
| 110 |
+
"eval_loss": 0.7818475365638733,
|
| 111 |
+
"eval_runtime": 12.8803,
|
| 112 |
+
"eval_samples_per_second": 707.05,
|
| 113 |
+
"eval_steps_per_second": 1.397,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.35,
|
| 118 |
+
"learning_rate": 8.571853116434189e-06,
|
| 119 |
+
"loss": 0.5325,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.35,
|
| 124 |
+
"eval_f1": 0.7735358044916588,
|
| 125 |
+
"eval_loss": 0.7993192672729492,
|
| 126 |
+
"eval_runtime": 12.9057,
|
| 127 |
+
"eval_samples_per_second": 705.655,
|
| 128 |
+
"eval_steps_per_second": 1.395,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.39,
|
| 133 |
+
"learning_rate": 8.430216415898262e-06,
|
| 134 |
+
"loss": 0.5428,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.39,
|
| 139 |
+
"eval_f1": 0.7840778670751144,
|
| 140 |
+
"eval_loss": 0.7405980229377747,
|
| 141 |
+
"eval_runtime": 12.8442,
|
| 142 |
+
"eval_samples_per_second": 709.036,
|
| 143 |
+
"eval_steps_per_second": 1.401,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.44,
|
| 148 |
+
"learning_rate": 8.288579715362338e-06,
|
| 149 |
+
"loss": 0.668,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.44,
|
| 154 |
+
"eval_f1": 0.808029787910792,
|
| 155 |
+
"eval_loss": 0.6355316042900085,
|
| 156 |
+
"eval_runtime": 12.7681,
|
| 157 |
+
"eval_samples_per_second": 713.26,
|
| 158 |
+
"eval_steps_per_second": 1.41,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.48,
|
| 163 |
+
"learning_rate": 8.146943014826413e-06,
|
| 164 |
+
"loss": 0.4458,
|
| 165 |
+
"step": 550
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.48,
|
| 169 |
+
"eval_f1": 0.7817572556557761,
|
| 170 |
+
"eval_loss": 0.7837744951248169,
|
| 171 |
+
"eval_runtime": 12.8958,
|
| 172 |
+
"eval_samples_per_second": 706.2,
|
| 173 |
+
"eval_steps_per_second": 1.396,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.53,
|
| 178 |
+
"learning_rate": 8.005306314290488e-06,
|
| 179 |
+
"loss": 0.5139,
|
| 180 |
+
"step": 600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.53,
|
| 184 |
+
"eval_f1": 0.8169684294224763,
|
| 185 |
+
"eval_loss": 0.6735610365867615,
|
| 186 |
+
"eval_runtime": 13.3617,
|
| 187 |
+
"eval_samples_per_second": 681.577,
|
| 188 |
+
"eval_steps_per_second": 1.347,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.57,
|
| 193 |
+
"learning_rate": 7.863669613754562e-06,
|
| 194 |
+
"loss": 0.678,
|
| 195 |
+
"step": 650
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.57,
|
| 199 |
+
"eval_f1": 0.8257079904308019,
|
| 200 |
+
"eval_loss": 0.6590014696121216,
|
| 201 |
+
"eval_runtime": 13.1257,
|
| 202 |
+
"eval_samples_per_second": 693.831,
|
| 203 |
+
"eval_steps_per_second": 1.371,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.61,
|
| 208 |
+
"learning_rate": 7.722032913218637e-06,
|
| 209 |
+
"loss": 0.7807,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.61,
|
| 214 |
+
"eval_f1": 0.8287897195977936,
|
| 215 |
+
"eval_loss": 0.5883087515830994,
|
| 216 |
+
"eval_runtime": 12.9111,
|
| 217 |
+
"eval_samples_per_second": 705.364,
|
| 218 |
+
"eval_steps_per_second": 1.394,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.66,
|
| 223 |
+
"learning_rate": 7.580396212682712e-06,
|
| 224 |
+
"loss": 0.4368,
|
| 225 |
+
"step": 750
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.66,
|
| 229 |
+
"eval_f1": 0.8027960747290149,
|
| 230 |
+
"eval_loss": 0.7591845393180847,
|
| 231 |
+
"eval_runtime": 12.9453,
|
| 232 |
+
"eval_samples_per_second": 703.499,
|
| 233 |
+
"eval_steps_per_second": 1.39,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7,
|
| 238 |
+
"learning_rate": 7.438759512146788e-06,
|
| 239 |
+
"loss": 0.5525,
|
| 240 |
+
"step": 800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7,
|
| 244 |
+
"eval_f1": 0.824382138583169,
|
| 245 |
+
"eval_loss": 0.671629011631012,
|
| 246 |
+
"eval_runtime": 13.4535,
|
| 247 |
+
"eval_samples_per_second": 676.924,
|
| 248 |
+
"eval_steps_per_second": 1.338,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.74,
|
| 253 |
+
"learning_rate": 7.297122811610861e-06,
|
| 254 |
+
"loss": 0.518,
|
| 255 |
+
"step": 850
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.74,
|
| 259 |
+
"eval_f1": 0.8091676627307244,
|
| 260 |
+
"eval_loss": 0.7957961559295654,
|
| 261 |
+
"eval_runtime": 13.0337,
|
| 262 |
+
"eval_samples_per_second": 698.728,
|
| 263 |
+
"eval_steps_per_second": 1.381,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.79,
|
| 268 |
+
"learning_rate": 7.1554861110749375e-06,
|
| 269 |
+
"loss": 0.6746,
|
| 270 |
+
"step": 900
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.79,
|
| 274 |
+
"eval_f1": 0.8209690397543833,
|
| 275 |
+
"eval_loss": 0.7072564363479614,
|
| 276 |
+
"eval_runtime": 13.0639,
|
| 277 |
+
"eval_samples_per_second": 697.112,
|
| 278 |
+
"eval_steps_per_second": 1.378,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.83,
|
| 283 |
+
"learning_rate": 7.013849410539012e-06,
|
| 284 |
+
"loss": 0.5969,
|
| 285 |
+
"step": 950
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.83,
|
| 289 |
+
"eval_f1": 0.8379639222695523,
|
| 290 |
+
"eval_loss": 0.6193687915802002,
|
| 291 |
+
"eval_runtime": 13.0113,
|
| 292 |
+
"eval_samples_per_second": 699.93,
|
| 293 |
+
"eval_steps_per_second": 1.383,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.88,
|
| 298 |
+
"learning_rate": 6.872212710003087e-06,
|
| 299 |
+
"loss": 0.4373,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.88,
|
| 304 |
+
"eval_f1": 0.819746814800145,
|
| 305 |
+
"eval_loss": 0.7536996006965637,
|
| 306 |
+
"eval_runtime": 12.7646,
|
| 307 |
+
"eval_samples_per_second": 713.459,
|
| 308 |
+
"eval_steps_per_second": 1.41,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.92,
|
| 313 |
+
"learning_rate": 6.730576009467162e-06,
|
| 314 |
+
"loss": 0.5211,
|
| 315 |
+
"step": 1050
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.92,
|
| 319 |
+
"eval_f1": 0.8111760271030569,
|
| 320 |
+
"eval_loss": 0.8388655781745911,
|
| 321 |
+
"eval_runtime": 12.9417,
|
| 322 |
+
"eval_samples_per_second": 703.696,
|
| 323 |
+
"eval_steps_per_second": 1.391,
|
| 324 |
+
"step": 1050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.96,
|
| 328 |
+
"learning_rate": 6.588939308931237e-06,
|
| 329 |
+
"loss": 0.6952,
|
| 330 |
+
"step": 1100
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.96,
|
| 334 |
+
"eval_f1": 0.816632917777235,
|
| 335 |
+
"eval_loss": 0.7328524589538574,
|
| 336 |
+
"eval_runtime": 13.5078,
|
| 337 |
+
"eval_samples_per_second": 674.203,
|
| 338 |
+
"eval_steps_per_second": 1.333,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.01,
|
| 343 |
+
"learning_rate": 6.447302608395311e-06,
|
| 344 |
+
"loss": 0.5314,
|
| 345 |
+
"step": 1150
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.01,
|
| 349 |
+
"eval_f1": 0.840661086405676,
|
| 350 |
+
"eval_loss": 0.6394931077957153,
|
| 351 |
+
"eval_runtime": 13.27,
|
| 352 |
+
"eval_samples_per_second": 686.284,
|
| 353 |
+
"eval_steps_per_second": 1.356,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.05,
|
| 358 |
+
"learning_rate": 6.305665907859387e-06,
|
| 359 |
+
"loss": 0.5489,
|
| 360 |
+
"step": 1200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.05,
|
| 364 |
+
"eval_f1": 0.8457657342031063,
|
| 365 |
+
"eval_loss": 0.6061137318611145,
|
| 366 |
+
"eval_runtime": 12.887,
|
| 367 |
+
"eval_samples_per_second": 706.68,
|
| 368 |
+
"eval_steps_per_second": 1.397,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.09,
|
| 373 |
+
"learning_rate": 6.164029207323461e-06,
|
| 374 |
+
"loss": 0.2584,
|
| 375 |
+
"step": 1250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.09,
|
| 379 |
+
"eval_f1": 0.8304659680514785,
|
| 380 |
+
"eval_loss": 0.7201290726661682,
|
| 381 |
+
"eval_runtime": 12.7847,
|
| 382 |
+
"eval_samples_per_second": 712.333,
|
| 383 |
+
"eval_steps_per_second": 1.408,
|
| 384 |
+
"step": 1250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.14,
|
| 388 |
+
"learning_rate": 6.022392506787536e-06,
|
| 389 |
+
"loss": 0.3589,
|
| 390 |
+
"step": 1300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.14,
|
| 394 |
+
"eval_f1": 0.8155619906391628,
|
| 395 |
+
"eval_loss": 0.818072497844696,
|
| 396 |
+
"eval_runtime": 13.0976,
|
| 397 |
+
"eval_samples_per_second": 695.318,
|
| 398 |
+
"eval_steps_per_second": 1.374,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.18,
|
| 403 |
+
"learning_rate": 5.880755806251611e-06,
|
| 404 |
+
"loss": 0.4149,
|
| 405 |
+
"step": 1350
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.18,
|
| 409 |
+
"eval_f1": 0.8441473560010259,
|
| 410 |
+
"eval_loss": 0.6451842784881592,
|
| 411 |
+
"eval_runtime": 13.134,
|
| 412 |
+
"eval_samples_per_second": 693.394,
|
| 413 |
+
"eval_steps_per_second": 1.37,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.23,
|
| 418 |
+
"learning_rate": 5.739119105715686e-06,
|
| 419 |
+
"loss": 0.3544,
|
| 420 |
+
"step": 1400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.23,
|
| 424 |
+
"eval_f1": 0.811124562539895,
|
| 425 |
+
"eval_loss": 0.8821828961372375,
|
| 426 |
+
"eval_runtime": 13.0791,
|
| 427 |
+
"eval_samples_per_second": 696.303,
|
| 428 |
+
"eval_steps_per_second": 1.376,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.27,
|
| 433 |
+
"learning_rate": 5.5974824051797605e-06,
|
| 434 |
+
"loss": 0.3952,
|
| 435 |
+
"step": 1450
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.27,
|
| 439 |
+
"eval_f1": 0.842967726161535,
|
| 440 |
+
"eval_loss": 0.6478109359741211,
|
| 441 |
+
"eval_runtime": 13.1787,
|
| 442 |
+
"eval_samples_per_second": 691.042,
|
| 443 |
+
"eval_steps_per_second": 1.366,
|
| 444 |
+
"step": 1450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.31,
|
| 448 |
+
"learning_rate": 5.455845704643836e-06,
|
| 449 |
+
"loss": 0.3582,
|
| 450 |
+
"step": 1500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.31,
|
| 454 |
+
"eval_f1": 0.8332197609307695,
|
| 455 |
+
"eval_loss": 0.7246124744415283,
|
| 456 |
+
"eval_runtime": 12.846,
|
| 457 |
+
"eval_samples_per_second": 708.936,
|
| 458 |
+
"eval_steps_per_second": 1.401,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.36,
|
| 463 |
+
"learning_rate": 5.31420900410791e-06,
|
| 464 |
+
"loss": 0.406,
|
| 465 |
+
"step": 1550
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.36,
|
| 469 |
+
"eval_f1": 0.8439420106874781,
|
| 470 |
+
"eval_loss": 0.7046599984169006,
|
| 471 |
+
"eval_runtime": 13.3454,
|
| 472 |
+
"eval_samples_per_second": 682.407,
|
| 473 |
+
"eval_steps_per_second": 1.349,
|
| 474 |
+
"step": 1550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.4,
|
| 478 |
+
"learning_rate": 5.1725723035719855e-06,
|
| 479 |
+
"loss": 0.2357,
|
| 480 |
+
"step": 1600
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.4,
|
| 484 |
+
"eval_f1": 0.8264183185065407,
|
| 485 |
+
"eval_loss": 0.7962601780891418,
|
| 486 |
+
"eval_runtime": 13.6369,
|
| 487 |
+
"eval_samples_per_second": 667.819,
|
| 488 |
+
"eval_steps_per_second": 1.32,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.44,
|
| 493 |
+
"learning_rate": 5.03093560303606e-06,
|
| 494 |
+
"loss": 0.4862,
|
| 495 |
+
"step": 1650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.44,
|
| 499 |
+
"eval_f1": 0.8396684697681687,
|
| 500 |
+
"eval_loss": 0.7174667119979858,
|
| 501 |
+
"eval_runtime": 13.2606,
|
| 502 |
+
"eval_samples_per_second": 686.77,
|
| 503 |
+
"eval_steps_per_second": 1.357,
|
| 504 |
+
"step": 1650
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.49,
|
| 508 |
+
"learning_rate": 4.889298902500135e-06,
|
| 509 |
+
"loss": 0.563,
|
| 510 |
+
"step": 1700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.49,
|
| 514 |
+
"eval_f1": 0.8279883655583724,
|
| 515 |
+
"eval_loss": 0.7731943726539612,
|
| 516 |
+
"eval_runtime": 12.885,
|
| 517 |
+
"eval_samples_per_second": 706.792,
|
| 518 |
+
"eval_steps_per_second": 1.397,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.53,
|
| 523 |
+
"learning_rate": 4.74766220196421e-06,
|
| 524 |
+
"loss": 0.6549,
|
| 525 |
+
"step": 1750
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.53,
|
| 529 |
+
"eval_f1": 0.8369189823677441,
|
| 530 |
+
"eval_loss": 0.7049793004989624,
|
| 531 |
+
"eval_runtime": 12.8452,
|
| 532 |
+
"eval_samples_per_second": 708.978,
|
| 533 |
+
"eval_steps_per_second": 1.401,
|
| 534 |
+
"step": 1750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.58,
|
| 538 |
+
"learning_rate": 4.606025501428285e-06,
|
| 539 |
+
"loss": 0.314,
|
| 540 |
+
"step": 1800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.58,
|
| 544 |
+
"eval_f1": 0.8262473782183439,
|
| 545 |
+
"eval_loss": 0.776759922504425,
|
| 546 |
+
"eval_runtime": 12.9836,
|
| 547 |
+
"eval_samples_per_second": 701.423,
|
| 548 |
+
"eval_steps_per_second": 1.386,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.62,
|
| 553 |
+
"learning_rate": 4.464388800892359e-06,
|
| 554 |
+
"loss": 0.4034,
|
| 555 |
+
"step": 1850
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.62,
|
| 559 |
+
"eval_f1": 0.828291371273197,
|
| 560 |
+
"eval_loss": 0.770912766456604,
|
| 561 |
+
"eval_runtime": 13.1595,
|
| 562 |
+
"eval_samples_per_second": 692.05,
|
| 563 |
+
"eval_steps_per_second": 1.368,
|
| 564 |
+
"step": 1850
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.66,
|
| 568 |
+
"learning_rate": 4.322752100356435e-06,
|
| 569 |
+
"loss": 0.3254,
|
| 570 |
+
"step": 1900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.66,
|
| 574 |
+
"eval_f1": 0.8198460970380873,
|
| 575 |
+
"eval_loss": 0.8465861082077026,
|
| 576 |
+
"eval_runtime": 13.1986,
|
| 577 |
+
"eval_samples_per_second": 689.998,
|
| 578 |
+
"eval_steps_per_second": 1.364,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.71,
|
| 583 |
+
"learning_rate": 4.181115399820509e-06,
|
| 584 |
+
"loss": 0.3468,
|
| 585 |
+
"step": 1950
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.71,
|
| 589 |
+
"eval_f1": 0.8192786806863037,
|
| 590 |
+
"eval_loss": 0.8381931781768799,
|
| 591 |
+
"eval_runtime": 12.9863,
|
| 592 |
+
"eval_samples_per_second": 701.277,
|
| 593 |
+
"eval_steps_per_second": 1.386,
|
| 594 |
+
"step": 1950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.75,
|
| 598 |
+
"learning_rate": 4.039478699284584e-06,
|
| 599 |
+
"loss": 0.4446,
|
| 600 |
+
"step": 2000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.75,
|
| 604 |
+
"eval_f1": 0.8268078717285056,
|
| 605 |
+
"eval_loss": 0.8162553906440735,
|
| 606 |
+
"eval_runtime": 13.1147,
|
| 607 |
+
"eval_samples_per_second": 694.411,
|
| 608 |
+
"eval_steps_per_second": 1.373,
|
| 609 |
+
"step": 2000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 50,
|
| 613 |
+
"max_steps": 3426,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 3,
|
| 616 |
+
"save_steps": 500,
|
| 617 |
+
"total_flos": 76494751048800.0,
|
| 618 |
+
"train_batch_size": 4,
|
| 619 |
+
"trial_name": null,
|
| 620 |
+
"trial_params": {
|
| 621 |
+
"learning_rate": 9.563310020185664e-06,
|
| 622 |
+
"num_train_epochs": 3,
|
| 623 |
+
"per_device_train_batch_size": 4,
|
| 624 |
+
"seed": 19
|
| 625 |
+
}
|
| 626 |
+
}
|
run-4/checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:195fa31c7a2d4667a2d2c6d2b553de97ab02341504737b177344f5bce61749ff
|
| 3 |
+
size 4728
|
run-4/checkpoint-2000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-4/checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5,
|
| 32 |
+
"LABEL_6": 6
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"max_position_embeddings": 514,
|
| 36 |
+
"model_type": "roberta",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "single_label_classification",
|
| 42 |
+
"tokenizer_class": "BertTokenizer",
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.37.0",
|
| 45 |
+
"type_vocab_size": 1,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 32000
|
| 48 |
+
}
|
run-4/checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6461af843c6c7333946db134fe7890d35e1dfc639af13611c714f9d8aa47db25
|
| 3 |
+
size 442518124
|
run-4/checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25d465ac93c0dc8a1101f295ea324bf0af9225c32b4fb921fd35c660c4b4f20d
|
| 3 |
+
size 885156090
|
run-4/checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:445a1e35e868cee47ba66975579565c115d07809ea76ff125345d1680da4385d
|
| 3 |
+
size 14244
|
run-4/checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffa1bfc556f558ecae0da5e3b4f3416f988411dedb374021683587cb13ffbfa8
|
| 3 |
+
size 1064
|
run-4/checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
run-4/checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-4/checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 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 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 512,
|
| 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 |
+
}
|
run-4/checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,776 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8394999850518816,
|
| 3 |
+
"best_model_checkpoint": "test-klue/ynat/run-4/checkpoint-2500",
|
| 4 |
+
"epoch": 2.189141856392294,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 9.563310020185664e-06,
|
| 14 |
+
"loss": 1.9366,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"eval_f1": 0.03217818600688812,
|
| 20 |
+
"eval_loss": 2.097200393676758,
|
| 21 |
+
"eval_runtime": 12.873,
|
| 22 |
+
"eval_samples_per_second": 707.45,
|
| 23 |
+
"eval_steps_per_second": 1.398,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09,
|
| 28 |
+
"learning_rate": 9.421673319649739e-06,
|
| 29 |
+
"loss": 1.7978,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09,
|
| 34 |
+
"eval_f1": 0.5091097821827345,
|
| 35 |
+
"eval_loss": 1.6588668823242188,
|
| 36 |
+
"eval_runtime": 13.4227,
|
| 37 |
+
"eval_samples_per_second": 678.477,
|
| 38 |
+
"eval_steps_per_second": 1.341,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 9.280036619113814e-06,
|
| 44 |
+
"loss": 1.021,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13,
|
| 49 |
+
"eval_f1": 0.6592011581290811,
|
| 50 |
+
"eval_loss": 1.1230525970458984,
|
| 51 |
+
"eval_runtime": 13.0831,
|
| 52 |
+
"eval_samples_per_second": 696.09,
|
| 53 |
+
"eval_steps_per_second": 1.376,
|
| 54 |
+
"step": 150
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.18,
|
| 58 |
+
"learning_rate": 9.13839991857789e-06,
|
| 59 |
+
"loss": 0.7302,
|
| 60 |
+
"step": 200
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.18,
|
| 64 |
+
"eval_f1": 0.627432664776629,
|
| 65 |
+
"eval_loss": 1.1058144569396973,
|
| 66 |
+
"eval_runtime": 12.7078,
|
| 67 |
+
"eval_samples_per_second": 716.644,
|
| 68 |
+
"eval_steps_per_second": 1.416,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.22,
|
| 73 |
+
"learning_rate": 8.996763218041963e-06,
|
| 74 |
+
"loss": 0.6429,
|
| 75 |
+
"step": 250
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.22,
|
| 79 |
+
"eval_f1": 0.734522756164717,
|
| 80 |
+
"eval_loss": 0.8953863382339478,
|
| 81 |
+
"eval_runtime": 12.6114,
|
| 82 |
+
"eval_samples_per_second": 722.125,
|
| 83 |
+
"eval_steps_per_second": 1.427,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.26,
|
| 88 |
+
"learning_rate": 8.855126517506038e-06,
|
| 89 |
+
"loss": 0.6025,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.26,
|
| 94 |
+
"eval_f1": 0.7221910843221135,
|
| 95 |
+
"eval_loss": 0.8775734305381775,
|
| 96 |
+
"eval_runtime": 12.7554,
|
| 97 |
+
"eval_samples_per_second": 713.971,
|
| 98 |
+
"eval_steps_per_second": 1.411,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.31,
|
| 103 |
+
"learning_rate": 8.713489816970114e-06,
|
| 104 |
+
"loss": 0.6414,
|
| 105 |
+
"step": 350
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.31,
|
| 109 |
+
"eval_f1": 0.7759207244222568,
|
| 110 |
+
"eval_loss": 0.7818475365638733,
|
| 111 |
+
"eval_runtime": 12.8803,
|
| 112 |
+
"eval_samples_per_second": 707.05,
|
| 113 |
+
"eval_steps_per_second": 1.397,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.35,
|
| 118 |
+
"learning_rate": 8.571853116434189e-06,
|
| 119 |
+
"loss": 0.5325,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.35,
|
| 124 |
+
"eval_f1": 0.7735358044916588,
|
| 125 |
+
"eval_loss": 0.7993192672729492,
|
| 126 |
+
"eval_runtime": 12.9057,
|
| 127 |
+
"eval_samples_per_second": 705.655,
|
| 128 |
+
"eval_steps_per_second": 1.395,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.39,
|
| 133 |
+
"learning_rate": 8.430216415898262e-06,
|
| 134 |
+
"loss": 0.5428,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.39,
|
| 139 |
+
"eval_f1": 0.7840778670751144,
|
| 140 |
+
"eval_loss": 0.7405980229377747,
|
| 141 |
+
"eval_runtime": 12.8442,
|
| 142 |
+
"eval_samples_per_second": 709.036,
|
| 143 |
+
"eval_steps_per_second": 1.401,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.44,
|
| 148 |
+
"learning_rate": 8.288579715362338e-06,
|
| 149 |
+
"loss": 0.668,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.44,
|
| 154 |
+
"eval_f1": 0.808029787910792,
|
| 155 |
+
"eval_loss": 0.6355316042900085,
|
| 156 |
+
"eval_runtime": 12.7681,
|
| 157 |
+
"eval_samples_per_second": 713.26,
|
| 158 |
+
"eval_steps_per_second": 1.41,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.48,
|
| 163 |
+
"learning_rate": 8.146943014826413e-06,
|
| 164 |
+
"loss": 0.4458,
|
| 165 |
+
"step": 550
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.48,
|
| 169 |
+
"eval_f1": 0.7817572556557761,
|
| 170 |
+
"eval_loss": 0.7837744951248169,
|
| 171 |
+
"eval_runtime": 12.8958,
|
| 172 |
+
"eval_samples_per_second": 706.2,
|
| 173 |
+
"eval_steps_per_second": 1.396,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.53,
|
| 178 |
+
"learning_rate": 8.005306314290488e-06,
|
| 179 |
+
"loss": 0.5139,
|
| 180 |
+
"step": 600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.53,
|
| 184 |
+
"eval_f1": 0.8169684294224763,
|
| 185 |
+
"eval_loss": 0.6735610365867615,
|
| 186 |
+
"eval_runtime": 13.3617,
|
| 187 |
+
"eval_samples_per_second": 681.577,
|
| 188 |
+
"eval_steps_per_second": 1.347,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.57,
|
| 193 |
+
"learning_rate": 7.863669613754562e-06,
|
| 194 |
+
"loss": 0.678,
|
| 195 |
+
"step": 650
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.57,
|
| 199 |
+
"eval_f1": 0.8257079904308019,
|
| 200 |
+
"eval_loss": 0.6590014696121216,
|
| 201 |
+
"eval_runtime": 13.1257,
|
| 202 |
+
"eval_samples_per_second": 693.831,
|
| 203 |
+
"eval_steps_per_second": 1.371,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.61,
|
| 208 |
+
"learning_rate": 7.722032913218637e-06,
|
| 209 |
+
"loss": 0.7807,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.61,
|
| 214 |
+
"eval_f1": 0.8287897195977936,
|
| 215 |
+
"eval_loss": 0.5883087515830994,
|
| 216 |
+
"eval_runtime": 12.9111,
|
| 217 |
+
"eval_samples_per_second": 705.364,
|
| 218 |
+
"eval_steps_per_second": 1.394,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.66,
|
| 223 |
+
"learning_rate": 7.580396212682712e-06,
|
| 224 |
+
"loss": 0.4368,
|
| 225 |
+
"step": 750
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.66,
|
| 229 |
+
"eval_f1": 0.8027960747290149,
|
| 230 |
+
"eval_loss": 0.7591845393180847,
|
| 231 |
+
"eval_runtime": 12.9453,
|
| 232 |
+
"eval_samples_per_second": 703.499,
|
| 233 |
+
"eval_steps_per_second": 1.39,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7,
|
| 238 |
+
"learning_rate": 7.438759512146788e-06,
|
| 239 |
+
"loss": 0.5525,
|
| 240 |
+
"step": 800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7,
|
| 244 |
+
"eval_f1": 0.824382138583169,
|
| 245 |
+
"eval_loss": 0.671629011631012,
|
| 246 |
+
"eval_runtime": 13.4535,
|
| 247 |
+
"eval_samples_per_second": 676.924,
|
| 248 |
+
"eval_steps_per_second": 1.338,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.74,
|
| 253 |
+
"learning_rate": 7.297122811610861e-06,
|
| 254 |
+
"loss": 0.518,
|
| 255 |
+
"step": 850
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.74,
|
| 259 |
+
"eval_f1": 0.8091676627307244,
|
| 260 |
+
"eval_loss": 0.7957961559295654,
|
| 261 |
+
"eval_runtime": 13.0337,
|
| 262 |
+
"eval_samples_per_second": 698.728,
|
| 263 |
+
"eval_steps_per_second": 1.381,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.79,
|
| 268 |
+
"learning_rate": 7.1554861110749375e-06,
|
| 269 |
+
"loss": 0.6746,
|
| 270 |
+
"step": 900
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.79,
|
| 274 |
+
"eval_f1": 0.8209690397543833,
|
| 275 |
+
"eval_loss": 0.7072564363479614,
|
| 276 |
+
"eval_runtime": 13.0639,
|
| 277 |
+
"eval_samples_per_second": 697.112,
|
| 278 |
+
"eval_steps_per_second": 1.378,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.83,
|
| 283 |
+
"learning_rate": 7.013849410539012e-06,
|
| 284 |
+
"loss": 0.5969,
|
| 285 |
+
"step": 950
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.83,
|
| 289 |
+
"eval_f1": 0.8379639222695523,
|
| 290 |
+
"eval_loss": 0.6193687915802002,
|
| 291 |
+
"eval_runtime": 13.0113,
|
| 292 |
+
"eval_samples_per_second": 699.93,
|
| 293 |
+
"eval_steps_per_second": 1.383,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.88,
|
| 298 |
+
"learning_rate": 6.872212710003087e-06,
|
| 299 |
+
"loss": 0.4373,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.88,
|
| 304 |
+
"eval_f1": 0.819746814800145,
|
| 305 |
+
"eval_loss": 0.7536996006965637,
|
| 306 |
+
"eval_runtime": 12.7646,
|
| 307 |
+
"eval_samples_per_second": 713.459,
|
| 308 |
+
"eval_steps_per_second": 1.41,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.92,
|
| 313 |
+
"learning_rate": 6.730576009467162e-06,
|
| 314 |
+
"loss": 0.5211,
|
| 315 |
+
"step": 1050
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.92,
|
| 319 |
+
"eval_f1": 0.8111760271030569,
|
| 320 |
+
"eval_loss": 0.8388655781745911,
|
| 321 |
+
"eval_runtime": 12.9417,
|
| 322 |
+
"eval_samples_per_second": 703.696,
|
| 323 |
+
"eval_steps_per_second": 1.391,
|
| 324 |
+
"step": 1050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.96,
|
| 328 |
+
"learning_rate": 6.588939308931237e-06,
|
| 329 |
+
"loss": 0.6952,
|
| 330 |
+
"step": 1100
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.96,
|
| 334 |
+
"eval_f1": 0.816632917777235,
|
| 335 |
+
"eval_loss": 0.7328524589538574,
|
| 336 |
+
"eval_runtime": 13.5078,
|
| 337 |
+
"eval_samples_per_second": 674.203,
|
| 338 |
+
"eval_steps_per_second": 1.333,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.01,
|
| 343 |
+
"learning_rate": 6.447302608395311e-06,
|
| 344 |
+
"loss": 0.5314,
|
| 345 |
+
"step": 1150
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.01,
|
| 349 |
+
"eval_f1": 0.840661086405676,
|
| 350 |
+
"eval_loss": 0.6394931077957153,
|
| 351 |
+
"eval_runtime": 13.27,
|
| 352 |
+
"eval_samples_per_second": 686.284,
|
| 353 |
+
"eval_steps_per_second": 1.356,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.05,
|
| 358 |
+
"learning_rate": 6.305665907859387e-06,
|
| 359 |
+
"loss": 0.5489,
|
| 360 |
+
"step": 1200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.05,
|
| 364 |
+
"eval_f1": 0.8457657342031063,
|
| 365 |
+
"eval_loss": 0.6061137318611145,
|
| 366 |
+
"eval_runtime": 12.887,
|
| 367 |
+
"eval_samples_per_second": 706.68,
|
| 368 |
+
"eval_steps_per_second": 1.397,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.09,
|
| 373 |
+
"learning_rate": 6.164029207323461e-06,
|
| 374 |
+
"loss": 0.2584,
|
| 375 |
+
"step": 1250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.09,
|
| 379 |
+
"eval_f1": 0.8304659680514785,
|
| 380 |
+
"eval_loss": 0.7201290726661682,
|
| 381 |
+
"eval_runtime": 12.7847,
|
| 382 |
+
"eval_samples_per_second": 712.333,
|
| 383 |
+
"eval_steps_per_second": 1.408,
|
| 384 |
+
"step": 1250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.14,
|
| 388 |
+
"learning_rate": 6.022392506787536e-06,
|
| 389 |
+
"loss": 0.3589,
|
| 390 |
+
"step": 1300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.14,
|
| 394 |
+
"eval_f1": 0.8155619906391628,
|
| 395 |
+
"eval_loss": 0.818072497844696,
|
| 396 |
+
"eval_runtime": 13.0976,
|
| 397 |
+
"eval_samples_per_second": 695.318,
|
| 398 |
+
"eval_steps_per_second": 1.374,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.18,
|
| 403 |
+
"learning_rate": 5.880755806251611e-06,
|
| 404 |
+
"loss": 0.4149,
|
| 405 |
+
"step": 1350
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.18,
|
| 409 |
+
"eval_f1": 0.8441473560010259,
|
| 410 |
+
"eval_loss": 0.6451842784881592,
|
| 411 |
+
"eval_runtime": 13.134,
|
| 412 |
+
"eval_samples_per_second": 693.394,
|
| 413 |
+
"eval_steps_per_second": 1.37,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.23,
|
| 418 |
+
"learning_rate": 5.739119105715686e-06,
|
| 419 |
+
"loss": 0.3544,
|
| 420 |
+
"step": 1400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.23,
|
| 424 |
+
"eval_f1": 0.811124562539895,
|
| 425 |
+
"eval_loss": 0.8821828961372375,
|
| 426 |
+
"eval_runtime": 13.0791,
|
| 427 |
+
"eval_samples_per_second": 696.303,
|
| 428 |
+
"eval_steps_per_second": 1.376,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.27,
|
| 433 |
+
"learning_rate": 5.5974824051797605e-06,
|
| 434 |
+
"loss": 0.3952,
|
| 435 |
+
"step": 1450
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.27,
|
| 439 |
+
"eval_f1": 0.842967726161535,
|
| 440 |
+
"eval_loss": 0.6478109359741211,
|
| 441 |
+
"eval_runtime": 13.1787,
|
| 442 |
+
"eval_samples_per_second": 691.042,
|
| 443 |
+
"eval_steps_per_second": 1.366,
|
| 444 |
+
"step": 1450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.31,
|
| 448 |
+
"learning_rate": 5.455845704643836e-06,
|
| 449 |
+
"loss": 0.3582,
|
| 450 |
+
"step": 1500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.31,
|
| 454 |
+
"eval_f1": 0.8332197609307695,
|
| 455 |
+
"eval_loss": 0.7246124744415283,
|
| 456 |
+
"eval_runtime": 12.846,
|
| 457 |
+
"eval_samples_per_second": 708.936,
|
| 458 |
+
"eval_steps_per_second": 1.401,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.36,
|
| 463 |
+
"learning_rate": 5.31420900410791e-06,
|
| 464 |
+
"loss": 0.406,
|
| 465 |
+
"step": 1550
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.36,
|
| 469 |
+
"eval_f1": 0.8439420106874781,
|
| 470 |
+
"eval_loss": 0.7046599984169006,
|
| 471 |
+
"eval_runtime": 13.3454,
|
| 472 |
+
"eval_samples_per_second": 682.407,
|
| 473 |
+
"eval_steps_per_second": 1.349,
|
| 474 |
+
"step": 1550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.4,
|
| 478 |
+
"learning_rate": 5.1725723035719855e-06,
|
| 479 |
+
"loss": 0.2357,
|
| 480 |
+
"step": 1600
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.4,
|
| 484 |
+
"eval_f1": 0.8264183185065407,
|
| 485 |
+
"eval_loss": 0.7962601780891418,
|
| 486 |
+
"eval_runtime": 13.6369,
|
| 487 |
+
"eval_samples_per_second": 667.819,
|
| 488 |
+
"eval_steps_per_second": 1.32,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.44,
|
| 493 |
+
"learning_rate": 5.03093560303606e-06,
|
| 494 |
+
"loss": 0.4862,
|
| 495 |
+
"step": 1650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.44,
|
| 499 |
+
"eval_f1": 0.8396684697681687,
|
| 500 |
+
"eval_loss": 0.7174667119979858,
|
| 501 |
+
"eval_runtime": 13.2606,
|
| 502 |
+
"eval_samples_per_second": 686.77,
|
| 503 |
+
"eval_steps_per_second": 1.357,
|
| 504 |
+
"step": 1650
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.49,
|
| 508 |
+
"learning_rate": 4.889298902500135e-06,
|
| 509 |
+
"loss": 0.563,
|
| 510 |
+
"step": 1700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.49,
|
| 514 |
+
"eval_f1": 0.8279883655583724,
|
| 515 |
+
"eval_loss": 0.7731943726539612,
|
| 516 |
+
"eval_runtime": 12.885,
|
| 517 |
+
"eval_samples_per_second": 706.792,
|
| 518 |
+
"eval_steps_per_second": 1.397,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.53,
|
| 523 |
+
"learning_rate": 4.74766220196421e-06,
|
| 524 |
+
"loss": 0.6549,
|
| 525 |
+
"step": 1750
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.53,
|
| 529 |
+
"eval_f1": 0.8369189823677441,
|
| 530 |
+
"eval_loss": 0.7049793004989624,
|
| 531 |
+
"eval_runtime": 12.8452,
|
| 532 |
+
"eval_samples_per_second": 708.978,
|
| 533 |
+
"eval_steps_per_second": 1.401,
|
| 534 |
+
"step": 1750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.58,
|
| 538 |
+
"learning_rate": 4.606025501428285e-06,
|
| 539 |
+
"loss": 0.314,
|
| 540 |
+
"step": 1800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.58,
|
| 544 |
+
"eval_f1": 0.8262473782183439,
|
| 545 |
+
"eval_loss": 0.776759922504425,
|
| 546 |
+
"eval_runtime": 12.9836,
|
| 547 |
+
"eval_samples_per_second": 701.423,
|
| 548 |
+
"eval_steps_per_second": 1.386,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.62,
|
| 553 |
+
"learning_rate": 4.464388800892359e-06,
|
| 554 |
+
"loss": 0.4034,
|
| 555 |
+
"step": 1850
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.62,
|
| 559 |
+
"eval_f1": 0.828291371273197,
|
| 560 |
+
"eval_loss": 0.770912766456604,
|
| 561 |
+
"eval_runtime": 13.1595,
|
| 562 |
+
"eval_samples_per_second": 692.05,
|
| 563 |
+
"eval_steps_per_second": 1.368,
|
| 564 |
+
"step": 1850
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.66,
|
| 568 |
+
"learning_rate": 4.322752100356435e-06,
|
| 569 |
+
"loss": 0.3254,
|
| 570 |
+
"step": 1900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.66,
|
| 574 |
+
"eval_f1": 0.8198460970380873,
|
| 575 |
+
"eval_loss": 0.8465861082077026,
|
| 576 |
+
"eval_runtime": 13.1986,
|
| 577 |
+
"eval_samples_per_second": 689.998,
|
| 578 |
+
"eval_steps_per_second": 1.364,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.71,
|
| 583 |
+
"learning_rate": 4.181115399820509e-06,
|
| 584 |
+
"loss": 0.3468,
|
| 585 |
+
"step": 1950
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.71,
|
| 589 |
+
"eval_f1": 0.8192786806863037,
|
| 590 |
+
"eval_loss": 0.8381931781768799,
|
| 591 |
+
"eval_runtime": 12.9863,
|
| 592 |
+
"eval_samples_per_second": 701.277,
|
| 593 |
+
"eval_steps_per_second": 1.386,
|
| 594 |
+
"step": 1950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.75,
|
| 598 |
+
"learning_rate": 4.039478699284584e-06,
|
| 599 |
+
"loss": 0.4446,
|
| 600 |
+
"step": 2000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.75,
|
| 604 |
+
"eval_f1": 0.8268078717285056,
|
| 605 |
+
"eval_loss": 0.8162553906440735,
|
| 606 |
+
"eval_runtime": 13.1147,
|
| 607 |
+
"eval_samples_per_second": 694.411,
|
| 608 |
+
"eval_steps_per_second": 1.373,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.8,
|
| 613 |
+
"learning_rate": 3.897841998748659e-06,
|
| 614 |
+
"loss": 0.3754,
|
| 615 |
+
"step": 2050
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.8,
|
| 619 |
+
"eval_f1": 0.8476155196237147,
|
| 620 |
+
"eval_loss": 0.6759063601493835,
|
| 621 |
+
"eval_runtime": 12.755,
|
| 622 |
+
"eval_samples_per_second": 713.996,
|
| 623 |
+
"eval_steps_per_second": 1.411,
|
| 624 |
+
"step": 2050
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.84,
|
| 628 |
+
"learning_rate": 3.7562052982127337e-06,
|
| 629 |
+
"loss": 0.4367,
|
| 630 |
+
"step": 2100
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.84,
|
| 634 |
+
"eval_f1": 0.8398306096663269,
|
| 635 |
+
"eval_loss": 0.7257468104362488,
|
| 636 |
+
"eval_runtime": 13.3134,
|
| 637 |
+
"eval_samples_per_second": 684.047,
|
| 638 |
+
"eval_steps_per_second": 1.352,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.88,
|
| 643 |
+
"learning_rate": 3.614568597676809e-06,
|
| 644 |
+
"loss": 0.5651,
|
| 645 |
+
"step": 2150
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.88,
|
| 649 |
+
"eval_f1": 0.8447688926358491,
|
| 650 |
+
"eval_loss": 0.7033412456512451,
|
| 651 |
+
"eval_runtime": 12.9921,
|
| 652 |
+
"eval_samples_per_second": 700.967,
|
| 653 |
+
"eval_steps_per_second": 1.385,
|
| 654 |
+
"step": 2150
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.93,
|
| 658 |
+
"learning_rate": 3.472931897140884e-06,
|
| 659 |
+
"loss": 0.4431,
|
| 660 |
+
"step": 2200
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.93,
|
| 664 |
+
"eval_f1": 0.8395472916895788,
|
| 665 |
+
"eval_loss": 0.7326067090034485,
|
| 666 |
+
"eval_runtime": 12.7433,
|
| 667 |
+
"eval_samples_per_second": 714.648,
|
| 668 |
+
"eval_steps_per_second": 1.413,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.97,
|
| 673 |
+
"learning_rate": 3.3312951966049587e-06,
|
| 674 |
+
"loss": 0.4206,
|
| 675 |
+
"step": 2250
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.97,
|
| 679 |
+
"eval_f1": 0.8427149926999598,
|
| 680 |
+
"eval_loss": 0.7332717180252075,
|
| 681 |
+
"eval_runtime": 12.7013,
|
| 682 |
+
"eval_samples_per_second": 717.011,
|
| 683 |
+
"eval_steps_per_second": 1.417,
|
| 684 |
+
"step": 2250
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.01,
|
| 688 |
+
"learning_rate": 3.1896584960690335e-06,
|
| 689 |
+
"loss": 0.5096,
|
| 690 |
+
"step": 2300
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.01,
|
| 694 |
+
"eval_f1": 0.8464156586502379,
|
| 695 |
+
"eval_loss": 0.6753610372543335,
|
| 696 |
+
"eval_runtime": 13.153,
|
| 697 |
+
"eval_samples_per_second": 692.389,
|
| 698 |
+
"eval_steps_per_second": 1.369,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.06,
|
| 703 |
+
"learning_rate": 3.0480217955331084e-06,
|
| 704 |
+
"loss": 0.2799,
|
| 705 |
+
"step": 2350
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.06,
|
| 709 |
+
"eval_f1": 0.8404557632892695,
|
| 710 |
+
"eval_loss": 0.7402009963989258,
|
| 711 |
+
"eval_runtime": 12.8771,
|
| 712 |
+
"eval_samples_per_second": 707.225,
|
| 713 |
+
"eval_steps_per_second": 1.398,
|
| 714 |
+
"step": 2350
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.1,
|
| 718 |
+
"learning_rate": 2.9063850949971833e-06,
|
| 719 |
+
"loss": 0.2175,
|
| 720 |
+
"step": 2400
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.1,
|
| 724 |
+
"eval_f1": 0.8434067060050701,
|
| 725 |
+
"eval_loss": 0.737072765827179,
|
| 726 |
+
"eval_runtime": 12.9539,
|
| 727 |
+
"eval_samples_per_second": 703.031,
|
| 728 |
+
"eval_steps_per_second": 1.39,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.15,
|
| 733 |
+
"learning_rate": 2.764748394461258e-06,
|
| 734 |
+
"loss": 0.1797,
|
| 735 |
+
"step": 2450
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.15,
|
| 739 |
+
"eval_f1": 0.8401881632037552,
|
| 740 |
+
"eval_loss": 0.7739103436470032,
|
| 741 |
+
"eval_runtime": 12.8086,
|
| 742 |
+
"eval_samples_per_second": 711.005,
|
| 743 |
+
"eval_steps_per_second": 1.405,
|
| 744 |
+
"step": 2450
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.19,
|
| 748 |
+
"learning_rate": 2.623111693925333e-06,
|
| 749 |
+
"loss": 0.2038,
|
| 750 |
+
"step": 2500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.19,
|
| 754 |
+
"eval_f1": 0.8394999850518816,
|
| 755 |
+
"eval_loss": 0.7923247218132019,
|
| 756 |
+
"eval_runtime": 12.8118,
|
| 757 |
+
"eval_samples_per_second": 710.827,
|
| 758 |
+
"eval_steps_per_second": 1.405,
|
| 759 |
+
"step": 2500
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 50,
|
| 763 |
+
"max_steps": 3426,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 3,
|
| 766 |
+
"save_steps": 500,
|
| 767 |
+
"total_flos": 95538268562400.0,
|
| 768 |
+
"train_batch_size": 4,
|
| 769 |
+
"trial_name": null,
|
| 770 |
+
"trial_params": {
|
| 771 |
+
"learning_rate": 9.563310020185664e-06,
|
| 772 |
+
"num_train_epochs": 3,
|
| 773 |
+
"per_device_train_batch_size": 4,
|
| 774 |
+
"seed": 19
|
| 775 |
+
}
|
| 776 |
+
}
|
run-4/checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:195fa31c7a2d4667a2d2c6d2b553de97ab02341504737b177344f5bce61749ff
|
| 3 |
+
size 4728
|
run-4/checkpoint-2500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|