Upload folder using huggingface_hub
Browse files- checkpoint-539/config.json +58 -0
- checkpoint-539/model.safetensors +3 -0
- checkpoint-539/optimizer.pt +3 -0
- checkpoint-539/rng_state.pth +3 -0
- checkpoint-539/scaler.pt +3 -0
- checkpoint-539/scheduler.pt +3 -0
- checkpoint-539/special_tokens_map.json +37 -0
- checkpoint-539/tokenizer.json +0 -0
- checkpoint-539/tokenizer_config.json +62 -0
- checkpoint-539/trainer_state.json +535 -0
- checkpoint-539/training_args.bin +3 -0
- checkpoint-539/vocab.txt +0 -0
- checkpoint-686/config.json +58 -0
- checkpoint-686/model.safetensors +3 -0
- checkpoint-686/optimizer.pt +3 -0
- checkpoint-686/rng_state.pth +3 -0
- checkpoint-686/scaler.pt +3 -0
- checkpoint-686/scheduler.pt +3 -0
- checkpoint-686/special_tokens_map.json +37 -0
- checkpoint-686/tokenizer.json +0 -0
- checkpoint-686/tokenizer_config.json +62 -0
- checkpoint-686/trainer_state.json +673 -0
- checkpoint-686/training_args.bin +3 -0
- checkpoint-686/vocab.txt +0 -0
- config.json +58 -0
- continual_metrics.json +10 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- thresholds_partial.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-539/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8",
|
| 22 |
+
"9": "LABEL_9",
|
| 23 |
+
"10": "LABEL_10"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"LABEL_0": 0,
|
| 29 |
+
"LABEL_1": 1,
|
| 30 |
+
"LABEL_10": 10,
|
| 31 |
+
"LABEL_2": 2,
|
| 32 |
+
"LABEL_3": 3,
|
| 33 |
+
"LABEL_4": 4,
|
| 34 |
+
"LABEL_5": 5,
|
| 35 |
+
"LABEL_6": 6,
|
| 36 |
+
"LABEL_7": 7,
|
| 37 |
+
"LABEL_8": 8,
|
| 38 |
+
"LABEL_9": 9
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-12,
|
| 41 |
+
"max_position_embeddings": 512,
|
| 42 |
+
"model_type": "bert",
|
| 43 |
+
"num_attention_heads": 12,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"output_past": true,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"pooler_fc_size": 768,
|
| 48 |
+
"pooler_num_attention_heads": 12,
|
| 49 |
+
"pooler_num_fc_layers": 3,
|
| 50 |
+
"pooler_size_per_head": 128,
|
| 51 |
+
"pooler_type": "first_token_transform",
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"problem_type": "multi_label_classification",
|
| 54 |
+
"transformers_version": "4.57.1",
|
| 55 |
+
"type_vocab_size": 2,
|
| 56 |
+
"use_cache": false,
|
| 57 |
+
"vocab_size": 119547
|
| 58 |
+
}
|
checkpoint-539/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c738cf16f89beea4a398280865fb780b4a0ed99e3a673fb9e36c1473ff993249
|
| 3 |
+
size 711471148
|
checkpoint-539/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:099a0f4166dd5965b764fe657452fb29eda6b125e46f5e007d268d2962ba883f
|
| 3 |
+
size 1423066507
|
checkpoint-539/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b683e3a8b696df210156cb5ce69eebd4ac8b9e6749907c84e151d36a41362a59
|
| 3 |
+
size 14645
|
checkpoint-539/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa1c28fbad6cb9d5603d765bad38f4102fe434942c5015a87551c7f290f382e
|
| 3 |
+
size 1383
|
checkpoint-539/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6133b37ec6e32a602470e01b3023d1c9a17b18381afeeda4383a748182bfb7f0
|
| 3 |
+
size 1465
|
checkpoint-539/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-539/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-539/tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"backend": "tokenizers",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"is_local": false,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 64,
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"tokenize_chinese_chars": true,
|
| 58 |
+
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "[UNK]"
|
| 62 |
+
}
|
checkpoint-539/trainer_state.json
ADDED
|
@@ -0,0 +1,535 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 539,
|
| 3 |
+
"best_metric": 0.7652582159624414,
|
| 4 |
+
"best_model_checkpoint": "/tmp/finetune/l2/checkpoint-539",
|
| 5 |
+
"epoch": 11.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 539,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.20408163265306123,
|
| 14 |
+
"grad_norm": 2.194807529449463,
|
| 15 |
+
"learning_rate": 6.081081081081082e-07,
|
| 16 |
+
"loss": 0.1998,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.40816326530612246,
|
| 21 |
+
"grad_norm": 5.4665727615356445,
|
| 22 |
+
"learning_rate": 1.2837837837837838e-06,
|
| 23 |
+
"loss": 0.2292,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6122448979591837,
|
| 28 |
+
"grad_norm": 5.707193851470947,
|
| 29 |
+
"learning_rate": 1.9594594594594595e-06,
|
| 30 |
+
"loss": 0.1915,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.8163265306122449,
|
| 35 |
+
"grad_norm": 7.533806800842285,
|
| 36 |
+
"learning_rate": 2.6351351351351353e-06,
|
| 37 |
+
"loss": 0.226,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_f1_macro": 0.7105381888127623,
|
| 43 |
+
"eval_f1_micro": 0.7078384798099763,
|
| 44 |
+
"eval_f1_weighted": 0.7004977849134466,
|
| 45 |
+
"eval_loss": 0.18318259716033936,
|
| 46 |
+
"eval_runtime": 0.6327,
|
| 47 |
+
"eval_samples_per_second": 305.038,
|
| 48 |
+
"eval_steps_per_second": 20.547,
|
| 49 |
+
"step": 49
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.0204081632653061,
|
| 53 |
+
"grad_norm": 7.434163570404053,
|
| 54 |
+
"learning_rate": 3.310810810810811e-06,
|
| 55 |
+
"loss": 0.2259,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.2244897959183674,
|
| 60 |
+
"grad_norm": 4.361626148223877,
|
| 61 |
+
"learning_rate": 3.986486486486487e-06,
|
| 62 |
+
"loss": 0.1761,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.4285714285714286,
|
| 67 |
+
"grad_norm": 4.420626640319824,
|
| 68 |
+
"learning_rate": 4.6621621621621625e-06,
|
| 69 |
+
"loss": 0.1844,
|
| 70 |
+
"step": 70
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.6326530612244898,
|
| 74 |
+
"grad_norm": 5.982855319976807,
|
| 75 |
+
"learning_rate": 4.962178517397882e-06,
|
| 76 |
+
"loss": 0.1538,
|
| 77 |
+
"step": 80
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.836734693877551,
|
| 81 |
+
"grad_norm": 3.9699554443359375,
|
| 82 |
+
"learning_rate": 4.886535552193646e-06,
|
| 83 |
+
"loss": 0.171,
|
| 84 |
+
"step": 90
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0,
|
| 88 |
+
"eval_f1_macro": 0.7073515633787281,
|
| 89 |
+
"eval_f1_micro": 0.7038834951456311,
|
| 90 |
+
"eval_f1_weighted": 0.6978974909161666,
|
| 91 |
+
"eval_loss": 0.17095711827278137,
|
| 92 |
+
"eval_runtime": 0.6497,
|
| 93 |
+
"eval_samples_per_second": 297.045,
|
| 94 |
+
"eval_steps_per_second": 20.008,
|
| 95 |
+
"step": 98
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.0408163265306123,
|
| 99 |
+
"grad_norm": 2.6549506187438965,
|
| 100 |
+
"learning_rate": 4.81089258698941e-06,
|
| 101 |
+
"loss": 0.1457,
|
| 102 |
+
"step": 100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.2448979591836733,
|
| 106 |
+
"grad_norm": 3.922772169113159,
|
| 107 |
+
"learning_rate": 4.7352496217851745e-06,
|
| 108 |
+
"loss": 0.1459,
|
| 109 |
+
"step": 110
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.4489795918367347,
|
| 113 |
+
"grad_norm": 4.702055931091309,
|
| 114 |
+
"learning_rate": 4.659606656580938e-06,
|
| 115 |
+
"loss": 0.1306,
|
| 116 |
+
"step": 120
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.6530612244897958,
|
| 120 |
+
"grad_norm": 4.254676818847656,
|
| 121 |
+
"learning_rate": 4.583963691376702e-06,
|
| 122 |
+
"loss": 0.1271,
|
| 123 |
+
"step": 130
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.857142857142857,
|
| 127 |
+
"grad_norm": 5.3793182373046875,
|
| 128 |
+
"learning_rate": 4.508320726172467e-06,
|
| 129 |
+
"loss": 0.1322,
|
| 130 |
+
"step": 140
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 3.0,
|
| 134 |
+
"eval_f1_macro": 0.7129027408610171,
|
| 135 |
+
"eval_f1_micro": 0.711864406779661,
|
| 136 |
+
"eval_f1_weighted": 0.7066061540411746,
|
| 137 |
+
"eval_loss": 0.16003255546092987,
|
| 138 |
+
"eval_runtime": 0.6269,
|
| 139 |
+
"eval_samples_per_second": 307.862,
|
| 140 |
+
"eval_steps_per_second": 20.737,
|
| 141 |
+
"step": 147
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.061224489795918,
|
| 145 |
+
"grad_norm": 4.1884002685546875,
|
| 146 |
+
"learning_rate": 4.43267776096823e-06,
|
| 147 |
+
"loss": 0.1339,
|
| 148 |
+
"step": 150
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.2653061224489797,
|
| 152 |
+
"grad_norm": 3.1676673889160156,
|
| 153 |
+
"learning_rate": 4.357034795763994e-06,
|
| 154 |
+
"loss": 0.1199,
|
| 155 |
+
"step": 160
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.4693877551020407,
|
| 159 |
+
"grad_norm": 6.360077857971191,
|
| 160 |
+
"learning_rate": 4.281391830559759e-06,
|
| 161 |
+
"loss": 0.1056,
|
| 162 |
+
"step": 170
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.673469387755102,
|
| 166 |
+
"grad_norm": 3.8555994033813477,
|
| 167 |
+
"learning_rate": 4.2057488653555225e-06,
|
| 168 |
+
"loss": 0.1199,
|
| 169 |
+
"step": 180
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.877551020408163,
|
| 173 |
+
"grad_norm": 5.292940616607666,
|
| 174 |
+
"learning_rate": 4.130105900151286e-06,
|
| 175 |
+
"loss": 0.1269,
|
| 176 |
+
"step": 190
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.0,
|
| 180 |
+
"eval_f1_macro": 0.739022809362487,
|
| 181 |
+
"eval_f1_micro": 0.7380952380952381,
|
| 182 |
+
"eval_f1_weighted": 0.7328483471625246,
|
| 183 |
+
"eval_loss": 0.15181854367256165,
|
| 184 |
+
"eval_runtime": 0.6262,
|
| 185 |
+
"eval_samples_per_second": 308.223,
|
| 186 |
+
"eval_steps_per_second": 20.761,
|
| 187 |
+
"step": 196
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.081632653061225,
|
| 191 |
+
"grad_norm": 2.861799478530884,
|
| 192 |
+
"learning_rate": 4.05446293494705e-06,
|
| 193 |
+
"loss": 0.0965,
|
| 194 |
+
"step": 200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.285714285714286,
|
| 198 |
+
"grad_norm": 2.875753164291382,
|
| 199 |
+
"learning_rate": 3.978819969742814e-06,
|
| 200 |
+
"loss": 0.107,
|
| 201 |
+
"step": 210
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.489795918367347,
|
| 205 |
+
"grad_norm": 3.6004979610443115,
|
| 206 |
+
"learning_rate": 3.9031770045385785e-06,
|
| 207 |
+
"loss": 0.1109,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.6938775510204085,
|
| 212 |
+
"grad_norm": 2.3077666759490967,
|
| 213 |
+
"learning_rate": 3.827534039334342e-06,
|
| 214 |
+
"loss": 0.1049,
|
| 215 |
+
"step": 230
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.8979591836734695,
|
| 219 |
+
"grad_norm": 4.845459938049316,
|
| 220 |
+
"learning_rate": 3.7518910741301064e-06,
|
| 221 |
+
"loss": 0.0933,
|
| 222 |
+
"step": 240
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.0,
|
| 226 |
+
"eval_f1_macro": 0.7462814517178719,
|
| 227 |
+
"eval_f1_micro": 0.7469879518072289,
|
| 228 |
+
"eval_f1_weighted": 0.7374498844458771,
|
| 229 |
+
"eval_loss": 0.151344895362854,
|
| 230 |
+
"eval_runtime": 0.6359,
|
| 231 |
+
"eval_samples_per_second": 303.506,
|
| 232 |
+
"eval_steps_per_second": 20.443,
|
| 233 |
+
"step": 245
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.1020408163265305,
|
| 237 |
+
"grad_norm": 3.957547664642334,
|
| 238 |
+
"learning_rate": 3.67624810892587e-06,
|
| 239 |
+
"loss": 0.1143,
|
| 240 |
+
"step": 250
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.3061224489795915,
|
| 244 |
+
"grad_norm": 2.440263509750366,
|
| 245 |
+
"learning_rate": 3.6006051437216344e-06,
|
| 246 |
+
"loss": 0.0842,
|
| 247 |
+
"step": 260
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.510204081632653,
|
| 251 |
+
"grad_norm": 2.0533766746520996,
|
| 252 |
+
"learning_rate": 3.524962178517398e-06,
|
| 253 |
+
"loss": 0.0835,
|
| 254 |
+
"step": 270
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.714285714285714,
|
| 258 |
+
"grad_norm": 2.234433174133301,
|
| 259 |
+
"learning_rate": 3.449319213313162e-06,
|
| 260 |
+
"loss": 0.0874,
|
| 261 |
+
"step": 280
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.918367346938775,
|
| 265 |
+
"grad_norm": 2.01436448097229,
|
| 266 |
+
"learning_rate": 3.3736762481089265e-06,
|
| 267 |
+
"loss": 0.0775,
|
| 268 |
+
"step": 290
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 6.0,
|
| 272 |
+
"eval_f1_macro": 0.7314792696872793,
|
| 273 |
+
"eval_f1_micro": 0.7320574162679426,
|
| 274 |
+
"eval_f1_weighted": 0.7229213437515356,
|
| 275 |
+
"eval_loss": 0.15624862909317017,
|
| 276 |
+
"eval_runtime": 0.6367,
|
| 277 |
+
"eval_samples_per_second": 303.142,
|
| 278 |
+
"eval_steps_per_second": 20.419,
|
| 279 |
+
"step": 294
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.122448979591836,
|
| 283 |
+
"grad_norm": 1.0920073986053467,
|
| 284 |
+
"learning_rate": 3.2980332829046903e-06,
|
| 285 |
+
"loss": 0.0948,
|
| 286 |
+
"step": 300
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 6.326530612244898,
|
| 290 |
+
"grad_norm": 2.755589723587036,
|
| 291 |
+
"learning_rate": 3.222390317700454e-06,
|
| 292 |
+
"loss": 0.0893,
|
| 293 |
+
"step": 310
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 6.530612244897959,
|
| 297 |
+
"grad_norm": 2.390260934829712,
|
| 298 |
+
"learning_rate": 3.1467473524962183e-06,
|
| 299 |
+
"loss": 0.0789,
|
| 300 |
+
"step": 320
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 6.73469387755102,
|
| 304 |
+
"grad_norm": 1.349293828010559,
|
| 305 |
+
"learning_rate": 3.071104387291982e-06,
|
| 306 |
+
"loss": 0.0778,
|
| 307 |
+
"step": 330
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 6.938775510204081,
|
| 311 |
+
"grad_norm": 3.054826498031616,
|
| 312 |
+
"learning_rate": 2.995461422087746e-06,
|
| 313 |
+
"loss": 0.0847,
|
| 314 |
+
"step": 340
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.0,
|
| 318 |
+
"eval_f1_macro": 0.7618238296226221,
|
| 319 |
+
"eval_f1_micro": 0.7612293144208038,
|
| 320 |
+
"eval_f1_weighted": 0.7539287865439286,
|
| 321 |
+
"eval_loss": 0.1503666639328003,
|
| 322 |
+
"eval_runtime": 0.6222,
|
| 323 |
+
"eval_samples_per_second": 310.189,
|
| 324 |
+
"eval_steps_per_second": 20.894,
|
| 325 |
+
"step": 343
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 7.142857142857143,
|
| 329 |
+
"grad_norm": 1.7866673469543457,
|
| 330 |
+
"learning_rate": 2.9198184568835104e-06,
|
| 331 |
+
"loss": 0.0691,
|
| 332 |
+
"step": 350
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.346938775510204,
|
| 336 |
+
"grad_norm": 1.9781595468521118,
|
| 337 |
+
"learning_rate": 2.844175491679274e-06,
|
| 338 |
+
"loss": 0.07,
|
| 339 |
+
"step": 360
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.551020408163265,
|
| 343 |
+
"grad_norm": 2.8111209869384766,
|
| 344 |
+
"learning_rate": 2.768532526475038e-06,
|
| 345 |
+
"loss": 0.0726,
|
| 346 |
+
"step": 370
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 7.755102040816326,
|
| 350 |
+
"grad_norm": 1.4259343147277832,
|
| 351 |
+
"learning_rate": 2.692889561270802e-06,
|
| 352 |
+
"loss": 0.0741,
|
| 353 |
+
"step": 380
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 7.959183673469388,
|
| 357 |
+
"grad_norm": 2.8336338996887207,
|
| 358 |
+
"learning_rate": 2.617246596066566e-06,
|
| 359 |
+
"loss": 0.0736,
|
| 360 |
+
"step": 390
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 8.0,
|
| 364 |
+
"eval_f1_macro": 0.7534406853518505,
|
| 365 |
+
"eval_f1_micro": 0.7553444180522565,
|
| 366 |
+
"eval_f1_weighted": 0.7471700863864514,
|
| 367 |
+
"eval_loss": 0.15129989385604858,
|
| 368 |
+
"eval_runtime": 0.6209,
|
| 369 |
+
"eval_samples_per_second": 310.845,
|
| 370 |
+
"eval_steps_per_second": 20.938,
|
| 371 |
+
"step": 392
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 8.16326530612245,
|
| 375 |
+
"grad_norm": 2.829455852508545,
|
| 376 |
+
"learning_rate": 2.5416036308623297e-06,
|
| 377 |
+
"loss": 0.0662,
|
| 378 |
+
"step": 400
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 8.36734693877551,
|
| 382 |
+
"grad_norm": 1.9278897047042847,
|
| 383 |
+
"learning_rate": 2.465960665658094e-06,
|
| 384 |
+
"loss": 0.076,
|
| 385 |
+
"step": 410
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 8.571428571428571,
|
| 389 |
+
"grad_norm": 2.8620712757110596,
|
| 390 |
+
"learning_rate": 2.390317700453858e-06,
|
| 391 |
+
"loss": 0.067,
|
| 392 |
+
"step": 420
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.775510204081632,
|
| 396 |
+
"grad_norm": 1.9797635078430176,
|
| 397 |
+
"learning_rate": 2.3146747352496223e-06,
|
| 398 |
+
"loss": 0.0662,
|
| 399 |
+
"step": 430
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 8.979591836734693,
|
| 403 |
+
"grad_norm": 1.4846246242523193,
|
| 404 |
+
"learning_rate": 2.239031770045386e-06,
|
| 405 |
+
"loss": 0.0634,
|
| 406 |
+
"step": 440
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 9.0,
|
| 410 |
+
"eval_f1_macro": 0.7480204045030746,
|
| 411 |
+
"eval_f1_micro": 0.7482352941176471,
|
| 412 |
+
"eval_f1_weighted": 0.7407760140152096,
|
| 413 |
+
"eval_loss": 0.1551072746515274,
|
| 414 |
+
"eval_runtime": 0.6159,
|
| 415 |
+
"eval_samples_per_second": 313.383,
|
| 416 |
+
"eval_steps_per_second": 21.109,
|
| 417 |
+
"step": 441
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 9.183673469387756,
|
| 421 |
+
"grad_norm": 3.946624755859375,
|
| 422 |
+
"learning_rate": 2.16338880484115e-06,
|
| 423 |
+
"loss": 0.0621,
|
| 424 |
+
"step": 450
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.387755102040817,
|
| 428 |
+
"grad_norm": 2.2177817821502686,
|
| 429 |
+
"learning_rate": 2.087745839636914e-06,
|
| 430 |
+
"loss": 0.0599,
|
| 431 |
+
"step": 460
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.591836734693878,
|
| 435 |
+
"grad_norm": 1.7603358030319214,
|
| 436 |
+
"learning_rate": 2.012102874432678e-06,
|
| 437 |
+
"loss": 0.0593,
|
| 438 |
+
"step": 470
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.795918367346939,
|
| 442 |
+
"grad_norm": 2.6135215759277344,
|
| 443 |
+
"learning_rate": 1.936459909228442e-06,
|
| 444 |
+
"loss": 0.0751,
|
| 445 |
+
"step": 480
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 10.0,
|
| 449 |
+
"grad_norm": 1.4198002815246582,
|
| 450 |
+
"learning_rate": 1.8608169440242058e-06,
|
| 451 |
+
"loss": 0.0598,
|
| 452 |
+
"step": 490
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.0,
|
| 456 |
+
"eval_f1_macro": 0.7630328262826187,
|
| 457 |
+
"eval_f1_micro": 0.7641509433962265,
|
| 458 |
+
"eval_f1_weighted": 0.758002840665604,
|
| 459 |
+
"eval_loss": 0.14575687050819397,
|
| 460 |
+
"eval_runtime": 1.1035,
|
| 461 |
+
"eval_samples_per_second": 174.899,
|
| 462 |
+
"eval_steps_per_second": 11.781,
|
| 463 |
+
"step": 490
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 10.204081632653061,
|
| 467 |
+
"grad_norm": 0.9668400883674622,
|
| 468 |
+
"learning_rate": 1.78517397881997e-06,
|
| 469 |
+
"loss": 0.0548,
|
| 470 |
+
"step": 500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 10.408163265306122,
|
| 474 |
+
"grad_norm": 2.780003547668457,
|
| 475 |
+
"learning_rate": 1.709531013615734e-06,
|
| 476 |
+
"loss": 0.0649,
|
| 477 |
+
"step": 510
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 10.612244897959183,
|
| 481 |
+
"grad_norm": 1.962121844291687,
|
| 482 |
+
"learning_rate": 1.6338880484114977e-06,
|
| 483 |
+
"loss": 0.0601,
|
| 484 |
+
"step": 520
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 10.816326530612244,
|
| 488 |
+
"grad_norm": 3.070321559906006,
|
| 489 |
+
"learning_rate": 1.5582450832072619e-06,
|
| 490 |
+
"loss": 0.0533,
|
| 491 |
+
"step": 530
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 11.0,
|
| 495 |
+
"eval_f1_macro": 0.765227079277026,
|
| 496 |
+
"eval_f1_micro": 0.7652582159624414,
|
| 497 |
+
"eval_f1_weighted": 0.7586082650718015,
|
| 498 |
+
"eval_loss": 0.14734649658203125,
|
| 499 |
+
"eval_runtime": 0.6627,
|
| 500 |
+
"eval_samples_per_second": 291.228,
|
| 501 |
+
"eval_steps_per_second": 19.616,
|
| 502 |
+
"step": 539
|
| 503 |
+
}
|
| 504 |
+
],
|
| 505 |
+
"logging_steps": 10,
|
| 506 |
+
"max_steps": 735,
|
| 507 |
+
"num_input_tokens_seen": 0,
|
| 508 |
+
"num_train_epochs": 15,
|
| 509 |
+
"save_steps": 500,
|
| 510 |
+
"stateful_callbacks": {
|
| 511 |
+
"EarlyStoppingCallback": {
|
| 512 |
+
"args": {
|
| 513 |
+
"early_stopping_patience": 3,
|
| 514 |
+
"early_stopping_threshold": 0.0
|
| 515 |
+
},
|
| 516 |
+
"attributes": {
|
| 517 |
+
"early_stopping_patience_counter": 0
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"TrainerControl": {
|
| 521 |
+
"args": {
|
| 522 |
+
"should_epoch_stop": false,
|
| 523 |
+
"should_evaluate": false,
|
| 524 |
+
"should_log": false,
|
| 525 |
+
"should_save": true,
|
| 526 |
+
"should_training_stop": false
|
| 527 |
+
},
|
| 528 |
+
"attributes": {}
|
| 529 |
+
}
|
| 530 |
+
},
|
| 531 |
+
"total_flos": 130948414108188.0,
|
| 532 |
+
"train_batch_size": 16,
|
| 533 |
+
"trial_name": null,
|
| 534 |
+
"trial_params": null
|
| 535 |
+
}
|
checkpoint-539/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a9348011aa9a8d4d179b7756a0372ae3af08bb16fd6d08d1e271d02aee39a5
|
| 3 |
+
size 5841
|
checkpoint-539/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-686/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8",
|
| 22 |
+
"9": "LABEL_9",
|
| 23 |
+
"10": "LABEL_10"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"LABEL_0": 0,
|
| 29 |
+
"LABEL_1": 1,
|
| 30 |
+
"LABEL_10": 10,
|
| 31 |
+
"LABEL_2": 2,
|
| 32 |
+
"LABEL_3": 3,
|
| 33 |
+
"LABEL_4": 4,
|
| 34 |
+
"LABEL_5": 5,
|
| 35 |
+
"LABEL_6": 6,
|
| 36 |
+
"LABEL_7": 7,
|
| 37 |
+
"LABEL_8": 8,
|
| 38 |
+
"LABEL_9": 9
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-12,
|
| 41 |
+
"max_position_embeddings": 512,
|
| 42 |
+
"model_type": "bert",
|
| 43 |
+
"num_attention_heads": 12,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"output_past": true,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"pooler_fc_size": 768,
|
| 48 |
+
"pooler_num_attention_heads": 12,
|
| 49 |
+
"pooler_num_fc_layers": 3,
|
| 50 |
+
"pooler_size_per_head": 128,
|
| 51 |
+
"pooler_type": "first_token_transform",
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"problem_type": "multi_label_classification",
|
| 54 |
+
"transformers_version": "4.57.1",
|
| 55 |
+
"type_vocab_size": 2,
|
| 56 |
+
"use_cache": false,
|
| 57 |
+
"vocab_size": 119547
|
| 58 |
+
}
|
checkpoint-686/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3d6729cbb78ecdf63befba7e9f1f997907d05bbee7e2eb2a22d91f00d487fe9
|
| 3 |
+
size 711471148
|
checkpoint-686/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53ce1f0f35311b88aba3cd5b31690dc51fb127fb556f61a0c197e4c18055db14
|
| 3 |
+
size 1423066507
|
checkpoint-686/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac17956d3d72bc591ef2dd1fd8579834d83ea58fb58d684b2c8a79588a23fa3
|
| 3 |
+
size 14645
|
checkpoint-686/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d0882c3d9728b1b6377a5b3ecab404cba06d14eee96c24726d6b4d2c470464d
|
| 3 |
+
size 1383
|
checkpoint-686/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3efedf2d4612e6214a221dcb51afa77f0c98c5e93f819dbd54e5bce7c2dbc11
|
| 3 |
+
size 1465
|
checkpoint-686/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-686/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-686/tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"backend": "tokenizers",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"is_local": false,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 64,
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"tokenize_chinese_chars": true,
|
| 58 |
+
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "[UNK]"
|
| 62 |
+
}
|
checkpoint-686/trainer_state.json
ADDED
|
@@ -0,0 +1,673 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 539,
|
| 3 |
+
"best_metric": 0.7652582159624414,
|
| 4 |
+
"best_model_checkpoint": "/tmp/finetune/l2/checkpoint-539",
|
| 5 |
+
"epoch": 14.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 686,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.20408163265306123,
|
| 14 |
+
"grad_norm": 2.194807529449463,
|
| 15 |
+
"learning_rate": 6.081081081081082e-07,
|
| 16 |
+
"loss": 0.1998,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.40816326530612246,
|
| 21 |
+
"grad_norm": 5.4665727615356445,
|
| 22 |
+
"learning_rate": 1.2837837837837838e-06,
|
| 23 |
+
"loss": 0.2292,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6122448979591837,
|
| 28 |
+
"grad_norm": 5.707193851470947,
|
| 29 |
+
"learning_rate": 1.9594594594594595e-06,
|
| 30 |
+
"loss": 0.1915,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.8163265306122449,
|
| 35 |
+
"grad_norm": 7.533806800842285,
|
| 36 |
+
"learning_rate": 2.6351351351351353e-06,
|
| 37 |
+
"loss": 0.226,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_f1_macro": 0.7105381888127623,
|
| 43 |
+
"eval_f1_micro": 0.7078384798099763,
|
| 44 |
+
"eval_f1_weighted": 0.7004977849134466,
|
| 45 |
+
"eval_loss": 0.18318259716033936,
|
| 46 |
+
"eval_runtime": 0.6327,
|
| 47 |
+
"eval_samples_per_second": 305.038,
|
| 48 |
+
"eval_steps_per_second": 20.547,
|
| 49 |
+
"step": 49
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.0204081632653061,
|
| 53 |
+
"grad_norm": 7.434163570404053,
|
| 54 |
+
"learning_rate": 3.310810810810811e-06,
|
| 55 |
+
"loss": 0.2259,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.2244897959183674,
|
| 60 |
+
"grad_norm": 4.361626148223877,
|
| 61 |
+
"learning_rate": 3.986486486486487e-06,
|
| 62 |
+
"loss": 0.1761,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.4285714285714286,
|
| 67 |
+
"grad_norm": 4.420626640319824,
|
| 68 |
+
"learning_rate": 4.6621621621621625e-06,
|
| 69 |
+
"loss": 0.1844,
|
| 70 |
+
"step": 70
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.6326530612244898,
|
| 74 |
+
"grad_norm": 5.982855319976807,
|
| 75 |
+
"learning_rate": 4.962178517397882e-06,
|
| 76 |
+
"loss": 0.1538,
|
| 77 |
+
"step": 80
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.836734693877551,
|
| 81 |
+
"grad_norm": 3.9699554443359375,
|
| 82 |
+
"learning_rate": 4.886535552193646e-06,
|
| 83 |
+
"loss": 0.171,
|
| 84 |
+
"step": 90
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0,
|
| 88 |
+
"eval_f1_macro": 0.7073515633787281,
|
| 89 |
+
"eval_f1_micro": 0.7038834951456311,
|
| 90 |
+
"eval_f1_weighted": 0.6978974909161666,
|
| 91 |
+
"eval_loss": 0.17095711827278137,
|
| 92 |
+
"eval_runtime": 0.6497,
|
| 93 |
+
"eval_samples_per_second": 297.045,
|
| 94 |
+
"eval_steps_per_second": 20.008,
|
| 95 |
+
"step": 98
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.0408163265306123,
|
| 99 |
+
"grad_norm": 2.6549506187438965,
|
| 100 |
+
"learning_rate": 4.81089258698941e-06,
|
| 101 |
+
"loss": 0.1457,
|
| 102 |
+
"step": 100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.2448979591836733,
|
| 106 |
+
"grad_norm": 3.922772169113159,
|
| 107 |
+
"learning_rate": 4.7352496217851745e-06,
|
| 108 |
+
"loss": 0.1459,
|
| 109 |
+
"step": 110
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.4489795918367347,
|
| 113 |
+
"grad_norm": 4.702055931091309,
|
| 114 |
+
"learning_rate": 4.659606656580938e-06,
|
| 115 |
+
"loss": 0.1306,
|
| 116 |
+
"step": 120
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.6530612244897958,
|
| 120 |
+
"grad_norm": 4.254676818847656,
|
| 121 |
+
"learning_rate": 4.583963691376702e-06,
|
| 122 |
+
"loss": 0.1271,
|
| 123 |
+
"step": 130
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.857142857142857,
|
| 127 |
+
"grad_norm": 5.3793182373046875,
|
| 128 |
+
"learning_rate": 4.508320726172467e-06,
|
| 129 |
+
"loss": 0.1322,
|
| 130 |
+
"step": 140
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 3.0,
|
| 134 |
+
"eval_f1_macro": 0.7129027408610171,
|
| 135 |
+
"eval_f1_micro": 0.711864406779661,
|
| 136 |
+
"eval_f1_weighted": 0.7066061540411746,
|
| 137 |
+
"eval_loss": 0.16003255546092987,
|
| 138 |
+
"eval_runtime": 0.6269,
|
| 139 |
+
"eval_samples_per_second": 307.862,
|
| 140 |
+
"eval_steps_per_second": 20.737,
|
| 141 |
+
"step": 147
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.061224489795918,
|
| 145 |
+
"grad_norm": 4.1884002685546875,
|
| 146 |
+
"learning_rate": 4.43267776096823e-06,
|
| 147 |
+
"loss": 0.1339,
|
| 148 |
+
"step": 150
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.2653061224489797,
|
| 152 |
+
"grad_norm": 3.1676673889160156,
|
| 153 |
+
"learning_rate": 4.357034795763994e-06,
|
| 154 |
+
"loss": 0.1199,
|
| 155 |
+
"step": 160
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.4693877551020407,
|
| 159 |
+
"grad_norm": 6.360077857971191,
|
| 160 |
+
"learning_rate": 4.281391830559759e-06,
|
| 161 |
+
"loss": 0.1056,
|
| 162 |
+
"step": 170
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.673469387755102,
|
| 166 |
+
"grad_norm": 3.8555994033813477,
|
| 167 |
+
"learning_rate": 4.2057488653555225e-06,
|
| 168 |
+
"loss": 0.1199,
|
| 169 |
+
"step": 180
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.877551020408163,
|
| 173 |
+
"grad_norm": 5.292940616607666,
|
| 174 |
+
"learning_rate": 4.130105900151286e-06,
|
| 175 |
+
"loss": 0.1269,
|
| 176 |
+
"step": 190
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.0,
|
| 180 |
+
"eval_f1_macro": 0.739022809362487,
|
| 181 |
+
"eval_f1_micro": 0.7380952380952381,
|
| 182 |
+
"eval_f1_weighted": 0.7328483471625246,
|
| 183 |
+
"eval_loss": 0.15181854367256165,
|
| 184 |
+
"eval_runtime": 0.6262,
|
| 185 |
+
"eval_samples_per_second": 308.223,
|
| 186 |
+
"eval_steps_per_second": 20.761,
|
| 187 |
+
"step": 196
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.081632653061225,
|
| 191 |
+
"grad_norm": 2.861799478530884,
|
| 192 |
+
"learning_rate": 4.05446293494705e-06,
|
| 193 |
+
"loss": 0.0965,
|
| 194 |
+
"step": 200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.285714285714286,
|
| 198 |
+
"grad_norm": 2.875753164291382,
|
| 199 |
+
"learning_rate": 3.978819969742814e-06,
|
| 200 |
+
"loss": 0.107,
|
| 201 |
+
"step": 210
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.489795918367347,
|
| 205 |
+
"grad_norm": 3.6004979610443115,
|
| 206 |
+
"learning_rate": 3.9031770045385785e-06,
|
| 207 |
+
"loss": 0.1109,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.6938775510204085,
|
| 212 |
+
"grad_norm": 2.3077666759490967,
|
| 213 |
+
"learning_rate": 3.827534039334342e-06,
|
| 214 |
+
"loss": 0.1049,
|
| 215 |
+
"step": 230
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.8979591836734695,
|
| 219 |
+
"grad_norm": 4.845459938049316,
|
| 220 |
+
"learning_rate": 3.7518910741301064e-06,
|
| 221 |
+
"loss": 0.0933,
|
| 222 |
+
"step": 240
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.0,
|
| 226 |
+
"eval_f1_macro": 0.7462814517178719,
|
| 227 |
+
"eval_f1_micro": 0.7469879518072289,
|
| 228 |
+
"eval_f1_weighted": 0.7374498844458771,
|
| 229 |
+
"eval_loss": 0.151344895362854,
|
| 230 |
+
"eval_runtime": 0.6359,
|
| 231 |
+
"eval_samples_per_second": 303.506,
|
| 232 |
+
"eval_steps_per_second": 20.443,
|
| 233 |
+
"step": 245
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.1020408163265305,
|
| 237 |
+
"grad_norm": 3.957547664642334,
|
| 238 |
+
"learning_rate": 3.67624810892587e-06,
|
| 239 |
+
"loss": 0.1143,
|
| 240 |
+
"step": 250
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.3061224489795915,
|
| 244 |
+
"grad_norm": 2.440263509750366,
|
| 245 |
+
"learning_rate": 3.6006051437216344e-06,
|
| 246 |
+
"loss": 0.0842,
|
| 247 |
+
"step": 260
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.510204081632653,
|
| 251 |
+
"grad_norm": 2.0533766746520996,
|
| 252 |
+
"learning_rate": 3.524962178517398e-06,
|
| 253 |
+
"loss": 0.0835,
|
| 254 |
+
"step": 270
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.714285714285714,
|
| 258 |
+
"grad_norm": 2.234433174133301,
|
| 259 |
+
"learning_rate": 3.449319213313162e-06,
|
| 260 |
+
"loss": 0.0874,
|
| 261 |
+
"step": 280
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.918367346938775,
|
| 265 |
+
"grad_norm": 2.01436448097229,
|
| 266 |
+
"learning_rate": 3.3736762481089265e-06,
|
| 267 |
+
"loss": 0.0775,
|
| 268 |
+
"step": 290
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 6.0,
|
| 272 |
+
"eval_f1_macro": 0.7314792696872793,
|
| 273 |
+
"eval_f1_micro": 0.7320574162679426,
|
| 274 |
+
"eval_f1_weighted": 0.7229213437515356,
|
| 275 |
+
"eval_loss": 0.15624862909317017,
|
| 276 |
+
"eval_runtime": 0.6367,
|
| 277 |
+
"eval_samples_per_second": 303.142,
|
| 278 |
+
"eval_steps_per_second": 20.419,
|
| 279 |
+
"step": 294
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.122448979591836,
|
| 283 |
+
"grad_norm": 1.0920073986053467,
|
| 284 |
+
"learning_rate": 3.2980332829046903e-06,
|
| 285 |
+
"loss": 0.0948,
|
| 286 |
+
"step": 300
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 6.326530612244898,
|
| 290 |
+
"grad_norm": 2.755589723587036,
|
| 291 |
+
"learning_rate": 3.222390317700454e-06,
|
| 292 |
+
"loss": 0.0893,
|
| 293 |
+
"step": 310
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 6.530612244897959,
|
| 297 |
+
"grad_norm": 2.390260934829712,
|
| 298 |
+
"learning_rate": 3.1467473524962183e-06,
|
| 299 |
+
"loss": 0.0789,
|
| 300 |
+
"step": 320
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 6.73469387755102,
|
| 304 |
+
"grad_norm": 1.349293828010559,
|
| 305 |
+
"learning_rate": 3.071104387291982e-06,
|
| 306 |
+
"loss": 0.0778,
|
| 307 |
+
"step": 330
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 6.938775510204081,
|
| 311 |
+
"grad_norm": 3.054826498031616,
|
| 312 |
+
"learning_rate": 2.995461422087746e-06,
|
| 313 |
+
"loss": 0.0847,
|
| 314 |
+
"step": 340
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.0,
|
| 318 |
+
"eval_f1_macro": 0.7618238296226221,
|
| 319 |
+
"eval_f1_micro": 0.7612293144208038,
|
| 320 |
+
"eval_f1_weighted": 0.7539287865439286,
|
| 321 |
+
"eval_loss": 0.1503666639328003,
|
| 322 |
+
"eval_runtime": 0.6222,
|
| 323 |
+
"eval_samples_per_second": 310.189,
|
| 324 |
+
"eval_steps_per_second": 20.894,
|
| 325 |
+
"step": 343
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 7.142857142857143,
|
| 329 |
+
"grad_norm": 1.7866673469543457,
|
| 330 |
+
"learning_rate": 2.9198184568835104e-06,
|
| 331 |
+
"loss": 0.0691,
|
| 332 |
+
"step": 350
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.346938775510204,
|
| 336 |
+
"grad_norm": 1.9781595468521118,
|
| 337 |
+
"learning_rate": 2.844175491679274e-06,
|
| 338 |
+
"loss": 0.07,
|
| 339 |
+
"step": 360
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.551020408163265,
|
| 343 |
+
"grad_norm": 2.8111209869384766,
|
| 344 |
+
"learning_rate": 2.768532526475038e-06,
|
| 345 |
+
"loss": 0.0726,
|
| 346 |
+
"step": 370
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 7.755102040816326,
|
| 350 |
+
"grad_norm": 1.4259343147277832,
|
| 351 |
+
"learning_rate": 2.692889561270802e-06,
|
| 352 |
+
"loss": 0.0741,
|
| 353 |
+
"step": 380
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 7.959183673469388,
|
| 357 |
+
"grad_norm": 2.8336338996887207,
|
| 358 |
+
"learning_rate": 2.617246596066566e-06,
|
| 359 |
+
"loss": 0.0736,
|
| 360 |
+
"step": 390
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 8.0,
|
| 364 |
+
"eval_f1_macro": 0.7534406853518505,
|
| 365 |
+
"eval_f1_micro": 0.7553444180522565,
|
| 366 |
+
"eval_f1_weighted": 0.7471700863864514,
|
| 367 |
+
"eval_loss": 0.15129989385604858,
|
| 368 |
+
"eval_runtime": 0.6209,
|
| 369 |
+
"eval_samples_per_second": 310.845,
|
| 370 |
+
"eval_steps_per_second": 20.938,
|
| 371 |
+
"step": 392
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 8.16326530612245,
|
| 375 |
+
"grad_norm": 2.829455852508545,
|
| 376 |
+
"learning_rate": 2.5416036308623297e-06,
|
| 377 |
+
"loss": 0.0662,
|
| 378 |
+
"step": 400
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 8.36734693877551,
|
| 382 |
+
"grad_norm": 1.9278897047042847,
|
| 383 |
+
"learning_rate": 2.465960665658094e-06,
|
| 384 |
+
"loss": 0.076,
|
| 385 |
+
"step": 410
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 8.571428571428571,
|
| 389 |
+
"grad_norm": 2.8620712757110596,
|
| 390 |
+
"learning_rate": 2.390317700453858e-06,
|
| 391 |
+
"loss": 0.067,
|
| 392 |
+
"step": 420
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.775510204081632,
|
| 396 |
+
"grad_norm": 1.9797635078430176,
|
| 397 |
+
"learning_rate": 2.3146747352496223e-06,
|
| 398 |
+
"loss": 0.0662,
|
| 399 |
+
"step": 430
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 8.979591836734693,
|
| 403 |
+
"grad_norm": 1.4846246242523193,
|
| 404 |
+
"learning_rate": 2.239031770045386e-06,
|
| 405 |
+
"loss": 0.0634,
|
| 406 |
+
"step": 440
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 9.0,
|
| 410 |
+
"eval_f1_macro": 0.7480204045030746,
|
| 411 |
+
"eval_f1_micro": 0.7482352941176471,
|
| 412 |
+
"eval_f1_weighted": 0.7407760140152096,
|
| 413 |
+
"eval_loss": 0.1551072746515274,
|
| 414 |
+
"eval_runtime": 0.6159,
|
| 415 |
+
"eval_samples_per_second": 313.383,
|
| 416 |
+
"eval_steps_per_second": 21.109,
|
| 417 |
+
"step": 441
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 9.183673469387756,
|
| 421 |
+
"grad_norm": 3.946624755859375,
|
| 422 |
+
"learning_rate": 2.16338880484115e-06,
|
| 423 |
+
"loss": 0.0621,
|
| 424 |
+
"step": 450
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.387755102040817,
|
| 428 |
+
"grad_norm": 2.2177817821502686,
|
| 429 |
+
"learning_rate": 2.087745839636914e-06,
|
| 430 |
+
"loss": 0.0599,
|
| 431 |
+
"step": 460
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.591836734693878,
|
| 435 |
+
"grad_norm": 1.7603358030319214,
|
| 436 |
+
"learning_rate": 2.012102874432678e-06,
|
| 437 |
+
"loss": 0.0593,
|
| 438 |
+
"step": 470
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.795918367346939,
|
| 442 |
+
"grad_norm": 2.6135215759277344,
|
| 443 |
+
"learning_rate": 1.936459909228442e-06,
|
| 444 |
+
"loss": 0.0751,
|
| 445 |
+
"step": 480
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 10.0,
|
| 449 |
+
"grad_norm": 1.4198002815246582,
|
| 450 |
+
"learning_rate": 1.8608169440242058e-06,
|
| 451 |
+
"loss": 0.0598,
|
| 452 |
+
"step": 490
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.0,
|
| 456 |
+
"eval_f1_macro": 0.7630328262826187,
|
| 457 |
+
"eval_f1_micro": 0.7641509433962265,
|
| 458 |
+
"eval_f1_weighted": 0.758002840665604,
|
| 459 |
+
"eval_loss": 0.14575687050819397,
|
| 460 |
+
"eval_runtime": 1.1035,
|
| 461 |
+
"eval_samples_per_second": 174.899,
|
| 462 |
+
"eval_steps_per_second": 11.781,
|
| 463 |
+
"step": 490
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 10.204081632653061,
|
| 467 |
+
"grad_norm": 0.9668400883674622,
|
| 468 |
+
"learning_rate": 1.78517397881997e-06,
|
| 469 |
+
"loss": 0.0548,
|
| 470 |
+
"step": 500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 10.408163265306122,
|
| 474 |
+
"grad_norm": 2.780003547668457,
|
| 475 |
+
"learning_rate": 1.709531013615734e-06,
|
| 476 |
+
"loss": 0.0649,
|
| 477 |
+
"step": 510
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 10.612244897959183,
|
| 481 |
+
"grad_norm": 1.962121844291687,
|
| 482 |
+
"learning_rate": 1.6338880484114977e-06,
|
| 483 |
+
"loss": 0.0601,
|
| 484 |
+
"step": 520
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 10.816326530612244,
|
| 488 |
+
"grad_norm": 3.070321559906006,
|
| 489 |
+
"learning_rate": 1.5582450832072619e-06,
|
| 490 |
+
"loss": 0.0533,
|
| 491 |
+
"step": 530
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 11.0,
|
| 495 |
+
"eval_f1_macro": 0.765227079277026,
|
| 496 |
+
"eval_f1_micro": 0.7652582159624414,
|
| 497 |
+
"eval_f1_weighted": 0.7586082650718015,
|
| 498 |
+
"eval_loss": 0.14734649658203125,
|
| 499 |
+
"eval_runtime": 0.6627,
|
| 500 |
+
"eval_samples_per_second": 291.228,
|
| 501 |
+
"eval_steps_per_second": 19.616,
|
| 502 |
+
"step": 539
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 11.020408163265307,
|
| 506 |
+
"grad_norm": 1.177020788192749,
|
| 507 |
+
"learning_rate": 1.4826021180030259e-06,
|
| 508 |
+
"loss": 0.0594,
|
| 509 |
+
"step": 540
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 11.224489795918368,
|
| 513 |
+
"grad_norm": 2.123314619064331,
|
| 514 |
+
"learning_rate": 1.4069591527987896e-06,
|
| 515 |
+
"loss": 0.067,
|
| 516 |
+
"step": 550
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.428571428571429,
|
| 520 |
+
"grad_norm": 2.1762566566467285,
|
| 521 |
+
"learning_rate": 1.3313161875945538e-06,
|
| 522 |
+
"loss": 0.0539,
|
| 523 |
+
"step": 560
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 11.63265306122449,
|
| 527 |
+
"grad_norm": 2.245833396911621,
|
| 528 |
+
"learning_rate": 1.2556732223903178e-06,
|
| 529 |
+
"loss": 0.0509,
|
| 530 |
+
"step": 570
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 11.83673469387755,
|
| 534 |
+
"grad_norm": 2.684638500213623,
|
| 535 |
+
"learning_rate": 1.1800302571860818e-06,
|
| 536 |
+
"loss": 0.062,
|
| 537 |
+
"step": 580
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 12.0,
|
| 541 |
+
"eval_f1_macro": 0.7567535089708038,
|
| 542 |
+
"eval_f1_micro": 0.7576470588235295,
|
| 543 |
+
"eval_f1_weighted": 0.7509842361549679,
|
| 544 |
+
"eval_loss": 0.14829698204994202,
|
| 545 |
+
"eval_runtime": 0.7076,
|
| 546 |
+
"eval_samples_per_second": 272.769,
|
| 547 |
+
"eval_steps_per_second": 18.373,
|
| 548 |
+
"step": 588
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 12.040816326530612,
|
| 552 |
+
"grad_norm": 2.823505163192749,
|
| 553 |
+
"learning_rate": 1.1043872919818458e-06,
|
| 554 |
+
"loss": 0.0652,
|
| 555 |
+
"step": 590
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 12.244897959183673,
|
| 559 |
+
"grad_norm": 1.1501375436782837,
|
| 560 |
+
"learning_rate": 1.0287443267776098e-06,
|
| 561 |
+
"loss": 0.0526,
|
| 562 |
+
"step": 600
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 12.448979591836734,
|
| 566 |
+
"grad_norm": 0.9779312014579773,
|
| 567 |
+
"learning_rate": 9.531013615733737e-07,
|
| 568 |
+
"loss": 0.0559,
|
| 569 |
+
"step": 610
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 12.653061224489797,
|
| 573 |
+
"grad_norm": 1.4313150644302368,
|
| 574 |
+
"learning_rate": 8.774583963691377e-07,
|
| 575 |
+
"loss": 0.0564,
|
| 576 |
+
"step": 620
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 12.857142857142858,
|
| 580 |
+
"grad_norm": 1.0637215375900269,
|
| 581 |
+
"learning_rate": 8.018154311649018e-07,
|
| 582 |
+
"loss": 0.0465,
|
| 583 |
+
"step": 630
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 13.0,
|
| 587 |
+
"eval_f1_macro": 0.7592902371289582,
|
| 588 |
+
"eval_f1_micro": 0.7605633802816901,
|
| 589 |
+
"eval_f1_weighted": 0.7520062793986627,
|
| 590 |
+
"eval_loss": 0.15075096487998962,
|
| 591 |
+
"eval_runtime": 0.654,
|
| 592 |
+
"eval_samples_per_second": 295.097,
|
| 593 |
+
"eval_steps_per_second": 19.877,
|
| 594 |
+
"step": 637
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.061224489795919,
|
| 598 |
+
"grad_norm": 1.843151330947876,
|
| 599 |
+
"learning_rate": 7.261724659606657e-07,
|
| 600 |
+
"loss": 0.0639,
|
| 601 |
+
"step": 640
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 13.26530612244898,
|
| 605 |
+
"grad_norm": 1.2329872846603394,
|
| 606 |
+
"learning_rate": 6.505295007564297e-07,
|
| 607 |
+
"loss": 0.0505,
|
| 608 |
+
"step": 650
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 13.46938775510204,
|
| 612 |
+
"grad_norm": 2.9725124835968018,
|
| 613 |
+
"learning_rate": 5.748865355521937e-07,
|
| 614 |
+
"loss": 0.058,
|
| 615 |
+
"step": 660
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 13.673469387755102,
|
| 619 |
+
"grad_norm": 0.6401973962783813,
|
| 620 |
+
"learning_rate": 4.992435703479577e-07,
|
| 621 |
+
"loss": 0.0536,
|
| 622 |
+
"step": 670
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 13.877551020408163,
|
| 626 |
+
"grad_norm": 1.913283348083496,
|
| 627 |
+
"learning_rate": 4.236006051437216e-07,
|
| 628 |
+
"loss": 0.0537,
|
| 629 |
+
"step": 680
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 14.0,
|
| 633 |
+
"eval_f1_macro": 0.7633703804435512,
|
| 634 |
+
"eval_f1_micro": 0.7634660421545667,
|
| 635 |
+
"eval_f1_weighted": 0.7576273254322035,
|
| 636 |
+
"eval_loss": 0.14885349571704865,
|
| 637 |
+
"eval_runtime": 0.6252,
|
| 638 |
+
"eval_samples_per_second": 308.709,
|
| 639 |
+
"eval_steps_per_second": 20.794,
|
| 640 |
+
"step": 686
|
| 641 |
+
}
|
| 642 |
+
],
|
| 643 |
+
"logging_steps": 10,
|
| 644 |
+
"max_steps": 735,
|
| 645 |
+
"num_input_tokens_seen": 0,
|
| 646 |
+
"num_train_epochs": 15,
|
| 647 |
+
"save_steps": 500,
|
| 648 |
+
"stateful_callbacks": {
|
| 649 |
+
"EarlyStoppingCallback": {
|
| 650 |
+
"args": {
|
| 651 |
+
"early_stopping_patience": 3,
|
| 652 |
+
"early_stopping_threshold": 0.0
|
| 653 |
+
},
|
| 654 |
+
"attributes": {
|
| 655 |
+
"early_stopping_patience_counter": 3
|
| 656 |
+
}
|
| 657 |
+
},
|
| 658 |
+
"TrainerControl": {
|
| 659 |
+
"args": {
|
| 660 |
+
"should_epoch_stop": false,
|
| 661 |
+
"should_evaluate": false,
|
| 662 |
+
"should_log": false,
|
| 663 |
+
"should_save": true,
|
| 664 |
+
"should_training_stop": true
|
| 665 |
+
},
|
| 666 |
+
"attributes": {}
|
| 667 |
+
}
|
| 668 |
+
},
|
| 669 |
+
"total_flos": 166515474865224.0,
|
| 670 |
+
"train_batch_size": 16,
|
| 671 |
+
"trial_name": null,
|
| 672 |
+
"trial_params": null
|
| 673 |
+
}
|
checkpoint-686/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a9348011aa9a8d4d179b7756a0372ae3af08bb16fd6d08d1e271d02aee39a5
|
| 3 |
+
size 5841
|
checkpoint-686/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8",
|
| 22 |
+
"9": "LABEL_9",
|
| 23 |
+
"10": "LABEL_10"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"LABEL_0": 0,
|
| 29 |
+
"LABEL_1": 1,
|
| 30 |
+
"LABEL_10": 10,
|
| 31 |
+
"LABEL_2": 2,
|
| 32 |
+
"LABEL_3": 3,
|
| 33 |
+
"LABEL_4": 4,
|
| 34 |
+
"LABEL_5": 5,
|
| 35 |
+
"LABEL_6": 6,
|
| 36 |
+
"LABEL_7": 7,
|
| 37 |
+
"LABEL_8": 8,
|
| 38 |
+
"LABEL_9": 9
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-12,
|
| 41 |
+
"max_position_embeddings": 512,
|
| 42 |
+
"model_type": "bert",
|
| 43 |
+
"num_attention_heads": 12,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"output_past": true,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"pooler_fc_size": 768,
|
| 48 |
+
"pooler_num_attention_heads": 12,
|
| 49 |
+
"pooler_num_fc_layers": 3,
|
| 50 |
+
"pooler_size_per_head": 128,
|
| 51 |
+
"pooler_type": "first_token_transform",
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"problem_type": "multi_label_classification",
|
| 54 |
+
"transformers_version": "4.57.1",
|
| 55 |
+
"type_vocab_size": 2,
|
| 56 |
+
"use_cache": false,
|
| 57 |
+
"vocab_size": 119547
|
| 58 |
+
}
|
continual_metrics.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_loss": 0.14734649658203125,
|
| 3 |
+
"eval_f1_micro": 0.7652582159624414,
|
| 4 |
+
"eval_f1_macro": 0.765227079277026,
|
| 5 |
+
"eval_f1_weighted": 0.7586082650718015,
|
| 6 |
+
"eval_runtime": 1.0355,
|
| 7 |
+
"eval_samples_per_second": 186.377,
|
| 8 |
+
"eval_steps_per_second": 12.554,
|
| 9 |
+
"epoch": 14.0
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c738cf16f89beea4a398280865fb780b4a0ed99e3a673fb9e36c1473ff993249
|
| 3 |
+
size 711471148
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
thresholds_partial.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Availability (A)": 0.6,
|
| 3 |
+
"Fault Tolerance (FT)": 0.35,
|
| 4 |
+
"Legal (L)": 0.35,
|
| 5 |
+
"Look & Feel (LF)": 0.15,
|
| 6 |
+
"Maintainability (MN)": 0.15,
|
| 7 |
+
"Operability (O)": 0.65,
|
| 8 |
+
"Performance (PE)": 0.9,
|
| 9 |
+
"Portability (PO)": 0.75,
|
| 10 |
+
"Scalability (SC)": 0.2,
|
| 11 |
+
"Security (SE)": 0.2,
|
| 12 |
+
"Usability (US)": 0.1
|
| 13 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"backend": "tokenizers",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"is_local": false,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 64,
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
+
"strip_accents": null,
|
| 57 |
+
"tokenize_chinese_chars": true,
|
| 58 |
+
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "[UNK]"
|
| 62 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a9348011aa9a8d4d179b7756a0372ae3af08bb16fd6d08d1e271d02aee39a5
|
| 3 |
+
size 5841
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|