Upload folder using huggingface_hub
Browse files- best_model/config.json +37 -0
- best_model/model.safetensors +3 -0
- best_model/special_tokens_map.json +7 -0
- best_model/tokenizer.json +0 -0
- best_model/tokenizer_config.json +59 -0
- best_model/training_args.bin +3 -0
- best_model/vocab.txt +0 -0
- checkpoint-7604/config.json +37 -0
- checkpoint-7604/model.safetensors +3 -0
- checkpoint-7604/optimizer.pt +3 -0
- checkpoint-7604/rng_state.pth +3 -0
- checkpoint-7604/scaler.pt +3 -0
- checkpoint-7604/scheduler.pt +3 -0
- checkpoint-7604/special_tokens_map.json +7 -0
- checkpoint-7604/tokenizer.json +0 -0
- checkpoint-7604/tokenizer_config.json +59 -0
- checkpoint-7604/trainer_state.json +1163 -0
- checkpoint-7604/training_args.bin +3 -0
- checkpoint-7604/vocab.txt +0 -0
- checkpoint-9505/config.json +37 -0
- checkpoint-9505/model.safetensors +3 -0
- checkpoint-9505/optimizer.pt +3 -0
- checkpoint-9505/rng_state.pth +3 -0
- checkpoint-9505/scaler.pt +3 -0
- checkpoint-9505/scheduler.pt +3 -0
- checkpoint-9505/special_tokens_map.json +7 -0
- checkpoint-9505/tokenizer.json +0 -0
- checkpoint-9505/tokenizer_config.json +59 -0
- checkpoint-9505/trainer_state.json +1443 -0
- checkpoint-9505/training_args.bin +3 -0
- checkpoint-9505/vocab.txt +0 -0
- confusion_matrix_val.csv +5 -0
- metrics.txt +1 -0
- val_predictions.csv +0 -0
best_model/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "aeb_Arab",
|
| 14 |
+
"1": "arb_Arab",
|
| 15 |
+
"2": "ars_Arab",
|
| 16 |
+
"3": "arz_Arab"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"aeb_Arab": 0,
|
| 22 |
+
"arb_Arab": 1,
|
| 23 |
+
"ars_Arab": 2,
|
| 24 |
+
"arz_Arab": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"transformers_version": "4.56.1",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30000
|
| 37 |
+
}
|
best_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:496bb5c365c925f55ceae6595a8e715b409815cc8b6ff91706c35fe83c24f363
|
| 3 |
+
size 436361208
|
best_model/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
best_model/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
best_model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
best_model/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa873479846449ff86b2d50d9e57056c48f72d07a9ffc1fb7f0012ac7d884f8
|
| 3 |
+
size 5777
|
best_model/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7604/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "aeb_Arab",
|
| 14 |
+
"1": "arb_Arab",
|
| 15 |
+
"2": "ars_Arab",
|
| 16 |
+
"3": "arz_Arab"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"aeb_Arab": 0,
|
| 22 |
+
"arb_Arab": 1,
|
| 23 |
+
"ars_Arab": 2,
|
| 24 |
+
"arz_Arab": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"transformers_version": "4.56.1",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30000
|
| 37 |
+
}
|
checkpoint-7604/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea97c9f54116987a4efce5003c237fe9ad14dba6bc8df6581b8e1b335acb132a
|
| 3 |
+
size 436361208
|
checkpoint-7604/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b377722c6852e6cbba0ccadd8c6526da27ed024558775d8e5aef375283656145
|
| 3 |
+
size 872846731
|
checkpoint-7604/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf843fc7bcd1af4ab3293b3c088707a5f43c002295ebaf38c7b73a37d8b8b6e2
|
| 3 |
+
size 14645
|
checkpoint-7604/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cff504aea448cd91d3c9132365ba5a6351fe5df0ebe126e322b53a9d87fdfb29
|
| 3 |
+
size 1383
|
checkpoint-7604/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df49cd2afd04bc85cb2837d2c80f823cd41bf926f70505d505372ff3c1aead5c
|
| 3 |
+
size 1465
|
checkpoint-7604/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-7604/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7604/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-7604/trainer_state.json
ADDED
|
@@ -0,0 +1,1163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 7604,
|
| 3 |
+
"best_metric": 0.9633717243752477,
|
| 4 |
+
"best_model_checkpoint": "camelbert_madar_task5/checkpoint-7604",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 7604,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.026301946344029457,
|
| 14 |
+
"grad_norm": 21.061479568481445,
|
| 15 |
+
"learning_rate": 1.9896896370331405e-05,
|
| 16 |
+
"loss": 0.9381,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.052603892688058915,
|
| 21 |
+
"grad_norm": 4.199251651763916,
|
| 22 |
+
"learning_rate": 1.9791688584955288e-05,
|
| 23 |
+
"loss": 0.5182,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07890583903208838,
|
| 28 |
+
"grad_norm": 22.227828979492188,
|
| 29 |
+
"learning_rate": 1.968648079957917e-05,
|
| 30 |
+
"loss": 0.4486,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.10520778537611783,
|
| 35 |
+
"grad_norm": 7.481734275817871,
|
| 36 |
+
"learning_rate": 1.9581273014203053e-05,
|
| 37 |
+
"loss": 0.4422,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1315097317201473,
|
| 42 |
+
"grad_norm": 9.7647705078125,
|
| 43 |
+
"learning_rate": 1.9476065228826936e-05,
|
| 44 |
+
"loss": 0.4304,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15781167806417676,
|
| 49 |
+
"grad_norm": 12.080931663513184,
|
| 50 |
+
"learning_rate": 1.9370857443450818e-05,
|
| 51 |
+
"loss": 0.3672,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1841136244082062,
|
| 56 |
+
"grad_norm": 11.353347778320312,
|
| 57 |
+
"learning_rate": 1.9265649658074697e-05,
|
| 58 |
+
"loss": 0.3771,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.21041557075223566,
|
| 63 |
+
"grad_norm": 3.3302719593048096,
|
| 64 |
+
"learning_rate": 1.916044187269858e-05,
|
| 65 |
+
"loss": 0.4053,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.23671751709626512,
|
| 70 |
+
"grad_norm": 11.869136810302734,
|
| 71 |
+
"learning_rate": 1.9055234087322463e-05,
|
| 72 |
+
"loss": 0.3754,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2630194634402946,
|
| 77 |
+
"grad_norm": 19.71166229248047,
|
| 78 |
+
"learning_rate": 1.8950026301946345e-05,
|
| 79 |
+
"loss": 0.3909,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.289321409784324,
|
| 84 |
+
"grad_norm": 82.08606719970703,
|
| 85 |
+
"learning_rate": 1.8844818516570228e-05,
|
| 86 |
+
"loss": 0.3945,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3156233561283535,
|
| 91 |
+
"grad_norm": 5.5329389572143555,
|
| 92 |
+
"learning_rate": 1.873961073119411e-05,
|
| 93 |
+
"loss": 0.3182,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.34192530247238295,
|
| 98 |
+
"grad_norm": 10.177448272705078,
|
| 99 |
+
"learning_rate": 1.8634402945817993e-05,
|
| 100 |
+
"loss": 0.3294,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3682272488164124,
|
| 105 |
+
"grad_norm": 11.596871376037598,
|
| 106 |
+
"learning_rate": 1.8529195160441876e-05,
|
| 107 |
+
"loss": 0.3445,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3945291951604419,
|
| 112 |
+
"grad_norm": 5.0095319747924805,
|
| 113 |
+
"learning_rate": 1.8423987375065758e-05,
|
| 114 |
+
"loss": 0.3403,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4208311415044713,
|
| 119 |
+
"grad_norm": 6.569547653198242,
|
| 120 |
+
"learning_rate": 1.8318779589689638e-05,
|
| 121 |
+
"loss": 0.2767,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4471330878485008,
|
| 126 |
+
"grad_norm": 7.269279956817627,
|
| 127 |
+
"learning_rate": 1.821357180431352e-05,
|
| 128 |
+
"loss": 0.3391,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.47343503419253025,
|
| 133 |
+
"grad_norm": 6.403675079345703,
|
| 134 |
+
"learning_rate": 1.8108364018937403e-05,
|
| 135 |
+
"loss": 0.2729,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4997369805365597,
|
| 140 |
+
"grad_norm": 18.03633689880371,
|
| 141 |
+
"learning_rate": 1.8003156233561285e-05,
|
| 142 |
+
"loss": 0.2912,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5260389268805892,
|
| 147 |
+
"grad_norm": 11.609797477722168,
|
| 148 |
+
"learning_rate": 1.7897948448185168e-05,
|
| 149 |
+
"loss": 0.3678,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.5523408732246187,
|
| 154 |
+
"grad_norm": 8.587767601013184,
|
| 155 |
+
"learning_rate": 1.779274066280905e-05,
|
| 156 |
+
"loss": 0.2789,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.578642819568648,
|
| 161 |
+
"grad_norm": 2.894766092300415,
|
| 162 |
+
"learning_rate": 1.768753287743293e-05,
|
| 163 |
+
"loss": 0.2515,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6049447659126775,
|
| 168 |
+
"grad_norm": 14.84619140625,
|
| 169 |
+
"learning_rate": 1.7582325092056812e-05,
|
| 170 |
+
"loss": 0.2817,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.631246712256707,
|
| 175 |
+
"grad_norm": 14.3659029006958,
|
| 176 |
+
"learning_rate": 1.7477117306680695e-05,
|
| 177 |
+
"loss": 0.2819,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6575486586007364,
|
| 182 |
+
"grad_norm": 24.962841033935547,
|
| 183 |
+
"learning_rate": 1.7371909521304578e-05,
|
| 184 |
+
"loss": 0.275,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.6838506049447659,
|
| 189 |
+
"grad_norm": 2.1663622856140137,
|
| 190 |
+
"learning_rate": 1.726670173592846e-05,
|
| 191 |
+
"loss": 0.2513,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.7101525512887954,
|
| 196 |
+
"grad_norm": 20.324939727783203,
|
| 197 |
+
"learning_rate": 1.7161493950552343e-05,
|
| 198 |
+
"loss": 0.2862,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7364544976328248,
|
| 203 |
+
"grad_norm": 12.115033149719238,
|
| 204 |
+
"learning_rate": 1.7056286165176222e-05,
|
| 205 |
+
"loss": 0.2489,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7627564439768543,
|
| 210 |
+
"grad_norm": 9.39247989654541,
|
| 211 |
+
"learning_rate": 1.6951078379800105e-05,
|
| 212 |
+
"loss": 0.2199,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.7890583903208838,
|
| 217 |
+
"grad_norm": 11.820609092712402,
|
| 218 |
+
"learning_rate": 1.684587059442399e-05,
|
| 219 |
+
"loss": 0.2334,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8153603366649133,
|
| 224 |
+
"grad_norm": 5.685638427734375,
|
| 225 |
+
"learning_rate": 1.6740662809047873e-05,
|
| 226 |
+
"loss": 0.2859,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8416622830089426,
|
| 231 |
+
"grad_norm": 1.4263566732406616,
|
| 232 |
+
"learning_rate": 1.6635455023671752e-05,
|
| 233 |
+
"loss": 0.2712,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.8679642293529721,
|
| 238 |
+
"grad_norm": 43.12693786621094,
|
| 239 |
+
"learning_rate": 1.6530247238295635e-05,
|
| 240 |
+
"loss": 0.2236,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.8942661756970016,
|
| 245 |
+
"grad_norm": 18.322067260742188,
|
| 246 |
+
"learning_rate": 1.6425039452919518e-05,
|
| 247 |
+
"loss": 0.2176,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.920568122041031,
|
| 252 |
+
"grad_norm": 8.125885009765625,
|
| 253 |
+
"learning_rate": 1.63198316675434e-05,
|
| 254 |
+
"loss": 0.2344,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.9468700683850605,
|
| 259 |
+
"grad_norm": 4.2774457931518555,
|
| 260 |
+
"learning_rate": 1.6214623882167283e-05,
|
| 261 |
+
"loss": 0.2173,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.97317201472909,
|
| 266 |
+
"grad_norm": 8.311309814453125,
|
| 267 |
+
"learning_rate": 1.6109416096791165e-05,
|
| 268 |
+
"loss": 0.207,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.9994739610731194,
|
| 273 |
+
"grad_norm": 18.770065307617188,
|
| 274 |
+
"learning_rate": 1.6004208311415045e-05,
|
| 275 |
+
"loss": 0.2261,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.0,
|
| 280 |
+
"eval_FPR_aeb_Arab": 0.007114016533913859,
|
| 281 |
+
"eval_FPR_arb_Arab": 0.007306287251046666,
|
| 282 |
+
"eval_FPR_ars_Arab": 0.0274961810821419,
|
| 283 |
+
"eval_FPR_arz_Arab": 0.03769230768505917,
|
| 284 |
+
"eval_accuracy": 0.9382975924220497,
|
| 285 |
+
"eval_loss": 0.2227914035320282,
|
| 286 |
+
"eval_macro_f1": 0.8929982487077235,
|
| 287 |
+
"eval_runtime": 3.3475,
|
| 288 |
+
"eval_samples_per_second": 2270.666,
|
| 289 |
+
"eval_steps_per_second": 35.549,
|
| 290 |
+
"step": 1901
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0257759074171489,
|
| 294 |
+
"grad_norm": 7.249199390411377,
|
| 295 |
+
"learning_rate": 1.5899000526038927e-05,
|
| 296 |
+
"loss": 0.1908,
|
| 297 |
+
"step": 1950
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0520778537611783,
|
| 301 |
+
"grad_norm": 16.18492889404297,
|
| 302 |
+
"learning_rate": 1.579379274066281e-05,
|
| 303 |
+
"loss": 0.1919,
|
| 304 |
+
"step": 2000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0783798001052078,
|
| 308 |
+
"grad_norm": 6.383620262145996,
|
| 309 |
+
"learning_rate": 1.5688584955286692e-05,
|
| 310 |
+
"loss": 0.1662,
|
| 311 |
+
"step": 2050
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.1046817464492373,
|
| 315 |
+
"grad_norm": 2.7821247577667236,
|
| 316 |
+
"learning_rate": 1.5583377169910575e-05,
|
| 317 |
+
"loss": 0.1832,
|
| 318 |
+
"step": 2100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1309836927932668,
|
| 322 |
+
"grad_norm": 0.20694231986999512,
|
| 323 |
+
"learning_rate": 1.5478169384534458e-05,
|
| 324 |
+
"loss": 0.1277,
|
| 325 |
+
"step": 2150
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.157285639137296,
|
| 329 |
+
"grad_norm": 66.66133880615234,
|
| 330 |
+
"learning_rate": 1.5372961599158337e-05,
|
| 331 |
+
"loss": 0.1896,
|
| 332 |
+
"step": 2200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1835875854813256,
|
| 336 |
+
"grad_norm": 5.3264055252075195,
|
| 337 |
+
"learning_rate": 1.526775381378222e-05,
|
| 338 |
+
"loss": 0.1535,
|
| 339 |
+
"step": 2250
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.209889531825355,
|
| 343 |
+
"grad_norm": 3.480900526046753,
|
| 344 |
+
"learning_rate": 1.5162546028406104e-05,
|
| 345 |
+
"loss": 0.1767,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2361914781693846,
|
| 350 |
+
"grad_norm": 2.1541006565093994,
|
| 351 |
+
"learning_rate": 1.5057338243029986e-05,
|
| 352 |
+
"loss": 0.2361,
|
| 353 |
+
"step": 2350
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.262493424513414,
|
| 357 |
+
"grad_norm": 13.037530899047852,
|
| 358 |
+
"learning_rate": 1.4952130457653869e-05,
|
| 359 |
+
"loss": 0.1733,
|
| 360 |
+
"step": 2400
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.2887953708574433,
|
| 364 |
+
"grad_norm": 6.1545281410217285,
|
| 365 |
+
"learning_rate": 1.484692267227775e-05,
|
| 366 |
+
"loss": 0.1608,
|
| 367 |
+
"step": 2450
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3150973172014728,
|
| 371 |
+
"grad_norm": 1.8223601579666138,
|
| 372 |
+
"learning_rate": 1.4741714886901633e-05,
|
| 373 |
+
"loss": 0.1746,
|
| 374 |
+
"step": 2500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3413992635455023,
|
| 378 |
+
"grad_norm": 3.253241777420044,
|
| 379 |
+
"learning_rate": 1.4636507101525515e-05,
|
| 380 |
+
"loss": 0.1466,
|
| 381 |
+
"step": 2550
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3677012098895318,
|
| 385 |
+
"grad_norm": 3.3945982456207275,
|
| 386 |
+
"learning_rate": 1.4531299316149396e-05,
|
| 387 |
+
"loss": 0.1732,
|
| 388 |
+
"step": 2600
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3940031562335613,
|
| 392 |
+
"grad_norm": 6.702133655548096,
|
| 393 |
+
"learning_rate": 1.4426091530773279e-05,
|
| 394 |
+
"loss": 0.2324,
|
| 395 |
+
"step": 2650
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.4203051025775908,
|
| 399 |
+
"grad_norm": 3.2291910648345947,
|
| 400 |
+
"learning_rate": 1.4320883745397161e-05,
|
| 401 |
+
"loss": 0.1615,
|
| 402 |
+
"step": 2700
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4466070489216203,
|
| 406 |
+
"grad_norm": 8.065141677856445,
|
| 407 |
+
"learning_rate": 1.4215675960021042e-05,
|
| 408 |
+
"loss": 0.1668,
|
| 409 |
+
"step": 2750
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.4729089952656498,
|
| 413 |
+
"grad_norm": 8.395434379577637,
|
| 414 |
+
"learning_rate": 1.4110468174644925e-05,
|
| 415 |
+
"loss": 0.2002,
|
| 416 |
+
"step": 2800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.499210941609679,
|
| 420 |
+
"grad_norm": 5.985948085784912,
|
| 421 |
+
"learning_rate": 1.4005260389268807e-05,
|
| 422 |
+
"loss": 0.1338,
|
| 423 |
+
"step": 2850
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.5255128879537085,
|
| 427 |
+
"grad_norm": 4.8504791259765625,
|
| 428 |
+
"learning_rate": 1.3900052603892688e-05,
|
| 429 |
+
"loss": 0.1493,
|
| 430 |
+
"step": 2900
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.551814834297738,
|
| 434 |
+
"grad_norm": 30.86811637878418,
|
| 435 |
+
"learning_rate": 1.3794844818516571e-05,
|
| 436 |
+
"loss": 0.1653,
|
| 437 |
+
"step": 2950
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.5781167806417675,
|
| 441 |
+
"grad_norm": 8.025301933288574,
|
| 442 |
+
"learning_rate": 1.3689637033140453e-05,
|
| 443 |
+
"loss": 0.195,
|
| 444 |
+
"step": 3000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.6044187269857968,
|
| 448 |
+
"grad_norm": 2.7844748497009277,
|
| 449 |
+
"learning_rate": 1.3584429247764334e-05,
|
| 450 |
+
"loss": 0.1513,
|
| 451 |
+
"step": 3050
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.6307206733298263,
|
| 455 |
+
"grad_norm": 15.212594032287598,
|
| 456 |
+
"learning_rate": 1.3479221462388219e-05,
|
| 457 |
+
"loss": 0.1311,
|
| 458 |
+
"step": 3100
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.6570226196738558,
|
| 462 |
+
"grad_norm": 7.984399795532227,
|
| 463 |
+
"learning_rate": 1.3374013677012101e-05,
|
| 464 |
+
"loss": 0.1699,
|
| 465 |
+
"step": 3150
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6833245660178853,
|
| 469 |
+
"grad_norm": 2.66343092918396,
|
| 470 |
+
"learning_rate": 1.3268805891635982e-05,
|
| 471 |
+
"loss": 0.0987,
|
| 472 |
+
"step": 3200
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.7096265123619148,
|
| 476 |
+
"grad_norm": 1.7281841039657593,
|
| 477 |
+
"learning_rate": 1.3163598106259865e-05,
|
| 478 |
+
"loss": 0.1468,
|
| 479 |
+
"step": 3250
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.7359284587059443,
|
| 483 |
+
"grad_norm": 80.2880859375,
|
| 484 |
+
"learning_rate": 1.3058390320883747e-05,
|
| 485 |
+
"loss": 0.1225,
|
| 486 |
+
"step": 3300
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7622304050499737,
|
| 490 |
+
"grad_norm": 3.2839515209198,
|
| 491 |
+
"learning_rate": 1.2953182535507628e-05,
|
| 492 |
+
"loss": 0.1612,
|
| 493 |
+
"step": 3350
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.7885323513940032,
|
| 497 |
+
"grad_norm": 6.35798978805542,
|
| 498 |
+
"learning_rate": 1.2847974750131511e-05,
|
| 499 |
+
"loss": 0.1319,
|
| 500 |
+
"step": 3400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.8148342977380327,
|
| 504 |
+
"grad_norm": 17.910255432128906,
|
| 505 |
+
"learning_rate": 1.2742766964755394e-05,
|
| 506 |
+
"loss": 0.2161,
|
| 507 |
+
"step": 3450
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.8411362440820622,
|
| 511 |
+
"grad_norm": 2.275036573410034,
|
| 512 |
+
"learning_rate": 1.2637559179379274e-05,
|
| 513 |
+
"loss": 0.1118,
|
| 514 |
+
"step": 3500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.8674381904260915,
|
| 518 |
+
"grad_norm": 20.091514587402344,
|
| 519 |
+
"learning_rate": 1.2532351394003157e-05,
|
| 520 |
+
"loss": 0.1463,
|
| 521 |
+
"step": 3550
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.893740136770121,
|
| 525 |
+
"grad_norm": 0.5615454912185669,
|
| 526 |
+
"learning_rate": 1.242714360862704e-05,
|
| 527 |
+
"loss": 0.1648,
|
| 528 |
+
"step": 3600
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.9200420831141505,
|
| 532 |
+
"grad_norm": 3.871091604232788,
|
| 533 |
+
"learning_rate": 1.232193582325092e-05,
|
| 534 |
+
"loss": 0.1325,
|
| 535 |
+
"step": 3650
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.9463440294581797,
|
| 539 |
+
"grad_norm": 1.768117904663086,
|
| 540 |
+
"learning_rate": 1.2216728037874803e-05,
|
| 541 |
+
"loss": 0.1664,
|
| 542 |
+
"step": 3700
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.9726459758022092,
|
| 546 |
+
"grad_norm": 5.8534393310546875,
|
| 547 |
+
"learning_rate": 1.2111520252498686e-05,
|
| 548 |
+
"loss": 0.1578,
|
| 549 |
+
"step": 3750
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.9989479221462387,
|
| 553 |
+
"grad_norm": 3.766312837600708,
|
| 554 |
+
"learning_rate": 1.2006312467122567e-05,
|
| 555 |
+
"loss": 0.1393,
|
| 556 |
+
"step": 3800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.0,
|
| 560 |
+
"eval_FPR_aeb_Arab": 0.00384541434265614,
|
| 561 |
+
"eval_FPR_arb_Arab": 0.02134204960174158,
|
| 562 |
+
"eval_FPR_ars_Arab": 0.01041522010687193,
|
| 563 |
+
"eval_FPR_arz_Arab": 0.020192307688424557,
|
| 564 |
+
"eval_accuracy": 0.9590843310090778,
|
| 565 |
+
"eval_loss": 0.16003794968128204,
|
| 566 |
+
"eval_macro_f1": 0.937683933464698,
|
| 567 |
+
"eval_runtime": 3.3754,
|
| 568 |
+
"eval_samples_per_second": 2251.882,
|
| 569 |
+
"eval_steps_per_second": 35.255,
|
| 570 |
+
"step": 3802
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0252498684902682,
|
| 574 |
+
"grad_norm": 14.620624542236328,
|
| 575 |
+
"learning_rate": 1.190110468174645e-05,
|
| 576 |
+
"loss": 0.073,
|
| 577 |
+
"step": 3850
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.0515518148342977,
|
| 581 |
+
"grad_norm": 1.2938824892044067,
|
| 582 |
+
"learning_rate": 1.1795896896370332e-05,
|
| 583 |
+
"loss": 0.1148,
|
| 584 |
+
"step": 3900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.077853761178327,
|
| 588 |
+
"grad_norm": 3.313081979751587,
|
| 589 |
+
"learning_rate": 1.1690689110994216e-05,
|
| 590 |
+
"loss": 0.0746,
|
| 591 |
+
"step": 3950
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.1041557075223567,
|
| 595 |
+
"grad_norm": 2.0338821411132812,
|
| 596 |
+
"learning_rate": 1.1585481325618097e-05,
|
| 597 |
+
"loss": 0.0977,
|
| 598 |
+
"step": 4000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.130457653866386,
|
| 602 |
+
"grad_norm": 0.055320367217063904,
|
| 603 |
+
"learning_rate": 1.148027354024198e-05,
|
| 604 |
+
"loss": 0.096,
|
| 605 |
+
"step": 4050
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.1567596002104157,
|
| 609 |
+
"grad_norm": 1.0964843034744263,
|
| 610 |
+
"learning_rate": 1.1375065754865862e-05,
|
| 611 |
+
"loss": 0.0642,
|
| 612 |
+
"step": 4100
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.183061546554445,
|
| 616 |
+
"grad_norm": 1.0340650081634521,
|
| 617 |
+
"learning_rate": 1.1269857969489743e-05,
|
| 618 |
+
"loss": 0.1007,
|
| 619 |
+
"step": 4150
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.2093634928984747,
|
| 623 |
+
"grad_norm": 4.971868515014648,
|
| 624 |
+
"learning_rate": 1.1164650184113626e-05,
|
| 625 |
+
"loss": 0.1083,
|
| 626 |
+
"step": 4200
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.2356654392425037,
|
| 630 |
+
"grad_norm": 0.49501538276672363,
|
| 631 |
+
"learning_rate": 1.1059442398737508e-05,
|
| 632 |
+
"loss": 0.1068,
|
| 633 |
+
"step": 4250
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.2619673855865337,
|
| 637 |
+
"grad_norm": 6.13097620010376,
|
| 638 |
+
"learning_rate": 1.095423461336139e-05,
|
| 639 |
+
"loss": 0.0946,
|
| 640 |
+
"step": 4300
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.2882693319305627,
|
| 644 |
+
"grad_norm": 5.904395580291748,
|
| 645 |
+
"learning_rate": 1.0849026827985272e-05,
|
| 646 |
+
"loss": 0.0758,
|
| 647 |
+
"step": 4350
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.314571278274592,
|
| 651 |
+
"grad_norm": 4.2567138671875,
|
| 652 |
+
"learning_rate": 1.0743819042609155e-05,
|
| 653 |
+
"loss": 0.111,
|
| 654 |
+
"step": 4400
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.3408732246186217,
|
| 658 |
+
"grad_norm": 0.1440172791481018,
|
| 659 |
+
"learning_rate": 1.0638611257233035e-05,
|
| 660 |
+
"loss": 0.1104,
|
| 661 |
+
"step": 4450
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.367175170962651,
|
| 665 |
+
"grad_norm": 7.970292091369629,
|
| 666 |
+
"learning_rate": 1.0533403471856918e-05,
|
| 667 |
+
"loss": 0.0891,
|
| 668 |
+
"step": 4500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.3934771173066807,
|
| 672 |
+
"grad_norm": 2.4047350883483887,
|
| 673 |
+
"learning_rate": 1.04281956864808e-05,
|
| 674 |
+
"loss": 0.1242,
|
| 675 |
+
"step": 4550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.41977906365071,
|
| 679 |
+
"grad_norm": 14.3352689743042,
|
| 680 |
+
"learning_rate": 1.0322987901104682e-05,
|
| 681 |
+
"loss": 0.0649,
|
| 682 |
+
"step": 4600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.4460810099947397,
|
| 686 |
+
"grad_norm": 25.1345157623291,
|
| 687 |
+
"learning_rate": 1.0217780115728564e-05,
|
| 688 |
+
"loss": 0.0712,
|
| 689 |
+
"step": 4650
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.472382956338769,
|
| 693 |
+
"grad_norm": 1.9517714977264404,
|
| 694 |
+
"learning_rate": 1.0112572330352445e-05,
|
| 695 |
+
"loss": 0.1032,
|
| 696 |
+
"step": 4700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.4986849026827986,
|
| 700 |
+
"grad_norm": 1.327062726020813,
|
| 701 |
+
"learning_rate": 1.000736454497633e-05,
|
| 702 |
+
"loss": 0.0962,
|
| 703 |
+
"step": 4750
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.524986849026828,
|
| 707 |
+
"grad_norm": 10.327136993408203,
|
| 708 |
+
"learning_rate": 9.90215675960021e-06,
|
| 709 |
+
"loss": 0.1092,
|
| 710 |
+
"step": 4800
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.5512887953708576,
|
| 714 |
+
"grad_norm": 3.8997962474823,
|
| 715 |
+
"learning_rate": 9.796948974224093e-06,
|
| 716 |
+
"loss": 0.0681,
|
| 717 |
+
"step": 4850
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.5775907417148867,
|
| 721 |
+
"grad_norm": 0.270841121673584,
|
| 722 |
+
"learning_rate": 9.691741188847975e-06,
|
| 723 |
+
"loss": 0.1265,
|
| 724 |
+
"step": 4900
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.6038926880589166,
|
| 728 |
+
"grad_norm": 0.8220506906509399,
|
| 729 |
+
"learning_rate": 9.586533403471858e-06,
|
| 730 |
+
"loss": 0.0726,
|
| 731 |
+
"step": 4950
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.6301946344029457,
|
| 735 |
+
"grad_norm": 1.4264813661575317,
|
| 736 |
+
"learning_rate": 9.48132561809574e-06,
|
| 737 |
+
"loss": 0.0707,
|
| 738 |
+
"step": 5000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.656496580746975,
|
| 742 |
+
"grad_norm": 5.427404880523682,
|
| 743 |
+
"learning_rate": 9.376117832719622e-06,
|
| 744 |
+
"loss": 0.0762,
|
| 745 |
+
"step": 5050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.6827985270910046,
|
| 749 |
+
"grad_norm": 39.103004455566406,
|
| 750 |
+
"learning_rate": 9.270910047343504e-06,
|
| 751 |
+
"loss": 0.0733,
|
| 752 |
+
"step": 5100
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.709100473435034,
|
| 756 |
+
"grad_norm": 2.8170275688171387,
|
| 757 |
+
"learning_rate": 9.165702261967387e-06,
|
| 758 |
+
"loss": 0.105,
|
| 759 |
+
"step": 5150
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.7354024197790636,
|
| 763 |
+
"grad_norm": 6.285243034362793,
|
| 764 |
+
"learning_rate": 9.060494476591268e-06,
|
| 765 |
+
"loss": 0.1054,
|
| 766 |
+
"step": 5200
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.761704366123093,
|
| 770 |
+
"grad_norm": 34.959102630615234,
|
| 771 |
+
"learning_rate": 8.95528669121515e-06,
|
| 772 |
+
"loss": 0.1168,
|
| 773 |
+
"step": 5250
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.7880063124671226,
|
| 777 |
+
"grad_norm": 2.698047399520874,
|
| 778 |
+
"learning_rate": 8.850078905839033e-06,
|
| 779 |
+
"loss": 0.0664,
|
| 780 |
+
"step": 5300
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.814308258811152,
|
| 784 |
+
"grad_norm": 6.107056617736816,
|
| 785 |
+
"learning_rate": 8.744871120462914e-06,
|
| 786 |
+
"loss": 0.0866,
|
| 787 |
+
"step": 5350
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.8406102051551816,
|
| 791 |
+
"grad_norm": 6.0492634773254395,
|
| 792 |
+
"learning_rate": 8.639663335086798e-06,
|
| 793 |
+
"loss": 0.0921,
|
| 794 |
+
"step": 5400
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.866912151499211,
|
| 798 |
+
"grad_norm": 38.75687789916992,
|
| 799 |
+
"learning_rate": 8.534455549710679e-06,
|
| 800 |
+
"loss": 0.0932,
|
| 801 |
+
"step": 5450
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.8932140978432406,
|
| 805 |
+
"grad_norm": 5.730583190917969,
|
| 806 |
+
"learning_rate": 8.429247764334562e-06,
|
| 807 |
+
"loss": 0.0809,
|
| 808 |
+
"step": 5500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.9195160441872696,
|
| 812 |
+
"grad_norm": 0.2023005187511444,
|
| 813 |
+
"learning_rate": 8.324039978958444e-06,
|
| 814 |
+
"loss": 0.0723,
|
| 815 |
+
"step": 5550
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.9458179905312996,
|
| 819 |
+
"grad_norm": 24.816850662231445,
|
| 820 |
+
"learning_rate": 8.218832193582325e-06,
|
| 821 |
+
"loss": 0.0758,
|
| 822 |
+
"step": 5600
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.9721199368753286,
|
| 826 |
+
"grad_norm": 0.10021505504846573,
|
| 827 |
+
"learning_rate": 8.113624408206208e-06,
|
| 828 |
+
"loss": 0.0787,
|
| 829 |
+
"step": 5650
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.998421883219358,
|
| 833 |
+
"grad_norm": 3.8389430046081543,
|
| 834 |
+
"learning_rate": 8.00841662283009e-06,
|
| 835 |
+
"loss": 0.1321,
|
| 836 |
+
"step": 5700
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.0,
|
| 840 |
+
"eval_FPR_aeb_Arab": 0.004037685059788947,
|
| 841 |
+
"eval_FPR_arb_Arab": 0.009421265139507543,
|
| 842 |
+
"eval_FPR_ars_Arab": 0.005971392861273241,
|
| 843 |
+
"eval_FPR_arz_Arab": 0.020192307688424557,
|
| 844 |
+
"eval_accuracy": 0.9713195632153664,
|
| 845 |
+
"eval_loss": 0.15336963534355164,
|
| 846 |
+
"eval_macro_f1": 0.9569564393242584,
|
| 847 |
+
"eval_runtime": 3.3689,
|
| 848 |
+
"eval_samples_per_second": 2256.259,
|
| 849 |
+
"eval_steps_per_second": 35.324,
|
| 850 |
+
"step": 5703
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 3.0247238295633876,
|
| 854 |
+
"grad_norm": 0.30554988980293274,
|
| 855 |
+
"learning_rate": 7.903208837453971e-06,
|
| 856 |
+
"loss": 0.0937,
|
| 857 |
+
"step": 5750
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.051025775907417,
|
| 861 |
+
"grad_norm": 37.439884185791016,
|
| 862 |
+
"learning_rate": 7.798001052077856e-06,
|
| 863 |
+
"loss": 0.0578,
|
| 864 |
+
"step": 5800
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.0773277222514466,
|
| 868 |
+
"grad_norm": 0.0822492390871048,
|
| 869 |
+
"learning_rate": 7.692793266701737e-06,
|
| 870 |
+
"loss": 0.0636,
|
| 871 |
+
"step": 5850
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.103629668595476,
|
| 875 |
+
"grad_norm": 2.7918007373809814,
|
| 876 |
+
"learning_rate": 7.587585481325619e-06,
|
| 877 |
+
"loss": 0.0378,
|
| 878 |
+
"step": 5900
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.1299316149395056,
|
| 882 |
+
"grad_norm": 32.899818420410156,
|
| 883 |
+
"learning_rate": 7.482377695949501e-06,
|
| 884 |
+
"loss": 0.0609,
|
| 885 |
+
"step": 5950
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.156233561283535,
|
| 889 |
+
"grad_norm": 0.06830895692110062,
|
| 890 |
+
"learning_rate": 7.377169910573383e-06,
|
| 891 |
+
"loss": 0.0433,
|
| 892 |
+
"step": 6000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.1825355076275645,
|
| 896 |
+
"grad_norm": 54.685489654541016,
|
| 897 |
+
"learning_rate": 7.271962125197265e-06,
|
| 898 |
+
"loss": 0.056,
|
| 899 |
+
"step": 6050
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.208837453971594,
|
| 903 |
+
"grad_norm": 0.8175523281097412,
|
| 904 |
+
"learning_rate": 7.166754339821147e-06,
|
| 905 |
+
"loss": 0.0341,
|
| 906 |
+
"step": 6100
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.2351394003156235,
|
| 910 |
+
"grad_norm": 0.33226722478866577,
|
| 911 |
+
"learning_rate": 7.061546554445029e-06,
|
| 912 |
+
"loss": 0.0482,
|
| 913 |
+
"step": 6150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.2614413466596526,
|
| 917 |
+
"grad_norm": 1.425661325454712,
|
| 918 |
+
"learning_rate": 6.956338769068912e-06,
|
| 919 |
+
"loss": 0.0673,
|
| 920 |
+
"step": 6200
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.2877432930036825,
|
| 924 |
+
"grad_norm": 0.18895921111106873,
|
| 925 |
+
"learning_rate": 6.851130983692794e-06,
|
| 926 |
+
"loss": 0.0359,
|
| 927 |
+
"step": 6250
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.3140452393477116,
|
| 931 |
+
"grad_norm": 0.6557305455207825,
|
| 932 |
+
"learning_rate": 6.7459231983166766e-06,
|
| 933 |
+
"loss": 0.0382,
|
| 934 |
+
"step": 6300
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.340347185691741,
|
| 938 |
+
"grad_norm": 0.008198770694434643,
|
| 939 |
+
"learning_rate": 6.640715412940558e-06,
|
| 940 |
+
"loss": 0.0566,
|
| 941 |
+
"step": 6350
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.3666491320357705,
|
| 945 |
+
"grad_norm": 0.4695976674556732,
|
| 946 |
+
"learning_rate": 6.53550762756444e-06,
|
| 947 |
+
"loss": 0.0654,
|
| 948 |
+
"step": 6400
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.3929510783798,
|
| 952 |
+
"grad_norm": 8.628214836120605,
|
| 953 |
+
"learning_rate": 6.430299842188323e-06,
|
| 954 |
+
"loss": 0.0427,
|
| 955 |
+
"step": 6450
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.4192530247238295,
|
| 959 |
+
"grad_norm": 0.9650713801383972,
|
| 960 |
+
"learning_rate": 6.3250920568122044e-06,
|
| 961 |
+
"loss": 0.0645,
|
| 962 |
+
"step": 6500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 3.445554971067859,
|
| 966 |
+
"grad_norm": 5.836668968200684,
|
| 967 |
+
"learning_rate": 6.219884271436086e-06,
|
| 968 |
+
"loss": 0.0397,
|
| 969 |
+
"step": 6550
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.4718569174118885,
|
| 973 |
+
"grad_norm": 0.03976545110344887,
|
| 974 |
+
"learning_rate": 6.11467648605997e-06,
|
| 975 |
+
"loss": 0.0586,
|
| 976 |
+
"step": 6600
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.498158863755918,
|
| 980 |
+
"grad_norm": 19.784215927124023,
|
| 981 |
+
"learning_rate": 6.009468700683851e-06,
|
| 982 |
+
"loss": 0.033,
|
| 983 |
+
"step": 6650
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.5244608100999475,
|
| 987 |
+
"grad_norm": 2.075496196746826,
|
| 988 |
+
"learning_rate": 5.904260915307733e-06,
|
| 989 |
+
"loss": 0.0776,
|
| 990 |
+
"step": 6700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 3.550762756443977,
|
| 994 |
+
"grad_norm": 7.05810022354126,
|
| 995 |
+
"learning_rate": 5.799053129931616e-06,
|
| 996 |
+
"loss": 0.0905,
|
| 997 |
+
"step": 6750
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 3.5770647027880065,
|
| 1001 |
+
"grad_norm": 0.012984913773834705,
|
| 1002 |
+
"learning_rate": 5.6938453445554975e-06,
|
| 1003 |
+
"loss": 0.0542,
|
| 1004 |
+
"step": 6800
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.6033666491320355,
|
| 1008 |
+
"grad_norm": 2.701481342315674,
|
| 1009 |
+
"learning_rate": 5.588637559179379e-06,
|
| 1010 |
+
"loss": 0.0625,
|
| 1011 |
+
"step": 6850
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 3.6296685954760655,
|
| 1015 |
+
"grad_norm": 0.41872379183769226,
|
| 1016 |
+
"learning_rate": 5.483429773803262e-06,
|
| 1017 |
+
"loss": 0.0795,
|
| 1018 |
+
"step": 6900
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 3.6559705418200945,
|
| 1022 |
+
"grad_norm": 0.13123294711112976,
|
| 1023 |
+
"learning_rate": 5.378221988427144e-06,
|
| 1024 |
+
"loss": 0.0296,
|
| 1025 |
+
"step": 6950
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.682272488164124,
|
| 1029 |
+
"grad_norm": 0.7190969586372375,
|
| 1030 |
+
"learning_rate": 5.273014203051027e-06,
|
| 1031 |
+
"loss": 0.0666,
|
| 1032 |
+
"step": 7000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 3.7085744345081535,
|
| 1036 |
+
"grad_norm": 0.1744261384010315,
|
| 1037 |
+
"learning_rate": 5.167806417674909e-06,
|
| 1038 |
+
"loss": 0.0328,
|
| 1039 |
+
"step": 7050
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 3.734876380852183,
|
| 1043 |
+
"grad_norm": 0.5619340538978577,
|
| 1044 |
+
"learning_rate": 5.062598632298791e-06,
|
| 1045 |
+
"loss": 0.0755,
|
| 1046 |
+
"step": 7100
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.7611783271962125,
|
| 1050 |
+
"grad_norm": 40.665706634521484,
|
| 1051 |
+
"learning_rate": 4.957390846922673e-06,
|
| 1052 |
+
"loss": 0.1041,
|
| 1053 |
+
"step": 7150
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 3.787480273540242,
|
| 1057 |
+
"grad_norm": 0.06617475301027298,
|
| 1058 |
+
"learning_rate": 4.852183061546555e-06,
|
| 1059 |
+
"loss": 0.0264,
|
| 1060 |
+
"step": 7200
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 3.8137822198842715,
|
| 1064 |
+
"grad_norm": 5.0283966064453125,
|
| 1065 |
+
"learning_rate": 4.746975276170437e-06,
|
| 1066 |
+
"loss": 0.0789,
|
| 1067 |
+
"step": 7250
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 3.840084166228301,
|
| 1071 |
+
"grad_norm": 5.660898208618164,
|
| 1072 |
+
"learning_rate": 4.641767490794319e-06,
|
| 1073 |
+
"loss": 0.0582,
|
| 1074 |
+
"step": 7300
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.8663861125723304,
|
| 1078 |
+
"grad_norm": 0.8503484725952148,
|
| 1079 |
+
"learning_rate": 4.536559705418201e-06,
|
| 1080 |
+
"loss": 0.0862,
|
| 1081 |
+
"step": 7350
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 3.89268805891636,
|
| 1085 |
+
"grad_norm": 13.575056076049805,
|
| 1086 |
+
"learning_rate": 4.431351920042084e-06,
|
| 1087 |
+
"loss": 0.0554,
|
| 1088 |
+
"step": 7400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.9189900052603894,
|
| 1092 |
+
"grad_norm": 0.25003504753112793,
|
| 1093 |
+
"learning_rate": 4.3261441346659654e-06,
|
| 1094 |
+
"loss": 0.0504,
|
| 1095 |
+
"step": 7450
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 3.9452919516044185,
|
| 1099 |
+
"grad_norm": 0.022247493267059326,
|
| 1100 |
+
"learning_rate": 4.220936349289847e-06,
|
| 1101 |
+
"loss": 0.0663,
|
| 1102 |
+
"step": 7500
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.9715938979484484,
|
| 1106 |
+
"grad_norm": 0.2591884136199951,
|
| 1107 |
+
"learning_rate": 4.11572856391373e-06,
|
| 1108 |
+
"loss": 0.0361,
|
| 1109 |
+
"step": 7550
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.9978958442924775,
|
| 1113 |
+
"grad_norm": 6.533713340759277,
|
| 1114 |
+
"learning_rate": 4.010520778537612e-06,
|
| 1115 |
+
"loss": 0.0293,
|
| 1116 |
+
"step": 7600
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.0,
|
| 1120 |
+
"eval_FPR_aeb_Arab": 0.004229955776921754,
|
| 1121 |
+
"eval_FPR_arb_Arab": 0.011343972310835613,
|
| 1122 |
+
"eval_FPR_ars_Arab": 0.00458269684702365,
|
| 1123 |
+
"eval_FPR_arz_Arab": 0.015576923073927515,
|
| 1124 |
+
"eval_accuracy": 0.9743454808577818,
|
| 1125 |
+
"eval_loss": 0.15085552632808685,
|
| 1126 |
+
"eval_macro_f1": 0.9633717243752477,
|
| 1127 |
+
"eval_runtime": 3.3689,
|
| 1128 |
+
"eval_samples_per_second": 2256.225,
|
| 1129 |
+
"eval_steps_per_second": 35.323,
|
| 1130 |
+
"step": 7604
|
| 1131 |
+
}
|
| 1132 |
+
],
|
| 1133 |
+
"logging_steps": 50,
|
| 1134 |
+
"max_steps": 9505,
|
| 1135 |
+
"num_input_tokens_seen": 0,
|
| 1136 |
+
"num_train_epochs": 5,
|
| 1137 |
+
"save_steps": 500,
|
| 1138 |
+
"stateful_callbacks": {
|
| 1139 |
+
"EarlyStoppingCallback": {
|
| 1140 |
+
"args": {
|
| 1141 |
+
"early_stopping_patience": 2,
|
| 1142 |
+
"early_stopping_threshold": 0.0
|
| 1143 |
+
},
|
| 1144 |
+
"attributes": {
|
| 1145 |
+
"early_stopping_patience_counter": 0
|
| 1146 |
+
}
|
| 1147 |
+
},
|
| 1148 |
+
"TrainerControl": {
|
| 1149 |
+
"args": {
|
| 1150 |
+
"should_epoch_stop": false,
|
| 1151 |
+
"should_evaluate": false,
|
| 1152 |
+
"should_log": false,
|
| 1153 |
+
"should_save": true,
|
| 1154 |
+
"should_training_stop": false
|
| 1155 |
+
},
|
| 1156 |
+
"attributes": {}
|
| 1157 |
+
}
|
| 1158 |
+
},
|
| 1159 |
+
"total_flos": 3440682832634112.0,
|
| 1160 |
+
"train_batch_size": 32,
|
| 1161 |
+
"trial_name": null,
|
| 1162 |
+
"trial_params": null
|
| 1163 |
+
}
|
checkpoint-7604/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa873479846449ff86b2d50d9e57056c48f72d07a9ffc1fb7f0012ac7d884f8
|
| 3 |
+
size 5777
|
checkpoint-7604/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-9505/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "aeb_Arab",
|
| 14 |
+
"1": "arb_Arab",
|
| 15 |
+
"2": "ars_Arab",
|
| 16 |
+
"3": "arz_Arab"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"aeb_Arab": 0,
|
| 22 |
+
"arb_Arab": 1,
|
| 23 |
+
"ars_Arab": 2,
|
| 24 |
+
"arz_Arab": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"transformers_version": "4.56.1",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30000
|
| 37 |
+
}
|
checkpoint-9505/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:496bb5c365c925f55ceae6595a8e715b409815cc8b6ff91706c35fe83c24f363
|
| 3 |
+
size 436361208
|
checkpoint-9505/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78fce8e6a78a3dd9090bb6fea2c41408a1f66de87245c884b78dcd7d0bf917fb
|
| 3 |
+
size 872846731
|
checkpoint-9505/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c65e00000d546fd729719d9d823f0bbe6b2fad692c4b49b96b131bba6b22e84b
|
| 3 |
+
size 14645
|
checkpoint-9505/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f176115dc4e83049fd3dff5a3ca9b4c02dc6d882e278af3ec1e96a2bcfccdaf
|
| 3 |
+
size 1383
|
checkpoint-9505/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e6a15eeffc5f00f2067bcaf3b35d9b2964df7e31ed9651c83e5191924ebd3b
|
| 3 |
+
size 1465
|
checkpoint-9505/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-9505/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-9505/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-9505/trainer_state.json
ADDED
|
@@ -0,0 +1,1443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 9505,
|
| 3 |
+
"best_metric": 0.9641750099415428,
|
| 4 |
+
"best_model_checkpoint": "camelbert_madar_task5/checkpoint-9505",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 9505,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.026301946344029457,
|
| 14 |
+
"grad_norm": 21.061479568481445,
|
| 15 |
+
"learning_rate": 1.9896896370331405e-05,
|
| 16 |
+
"loss": 0.9381,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.052603892688058915,
|
| 21 |
+
"grad_norm": 4.199251651763916,
|
| 22 |
+
"learning_rate": 1.9791688584955288e-05,
|
| 23 |
+
"loss": 0.5182,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07890583903208838,
|
| 28 |
+
"grad_norm": 22.227828979492188,
|
| 29 |
+
"learning_rate": 1.968648079957917e-05,
|
| 30 |
+
"loss": 0.4486,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.10520778537611783,
|
| 35 |
+
"grad_norm": 7.481734275817871,
|
| 36 |
+
"learning_rate": 1.9581273014203053e-05,
|
| 37 |
+
"loss": 0.4422,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1315097317201473,
|
| 42 |
+
"grad_norm": 9.7647705078125,
|
| 43 |
+
"learning_rate": 1.9476065228826936e-05,
|
| 44 |
+
"loss": 0.4304,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15781167806417676,
|
| 49 |
+
"grad_norm": 12.080931663513184,
|
| 50 |
+
"learning_rate": 1.9370857443450818e-05,
|
| 51 |
+
"loss": 0.3672,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1841136244082062,
|
| 56 |
+
"grad_norm": 11.353347778320312,
|
| 57 |
+
"learning_rate": 1.9265649658074697e-05,
|
| 58 |
+
"loss": 0.3771,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.21041557075223566,
|
| 63 |
+
"grad_norm": 3.3302719593048096,
|
| 64 |
+
"learning_rate": 1.916044187269858e-05,
|
| 65 |
+
"loss": 0.4053,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.23671751709626512,
|
| 70 |
+
"grad_norm": 11.869136810302734,
|
| 71 |
+
"learning_rate": 1.9055234087322463e-05,
|
| 72 |
+
"loss": 0.3754,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2630194634402946,
|
| 77 |
+
"grad_norm": 19.71166229248047,
|
| 78 |
+
"learning_rate": 1.8950026301946345e-05,
|
| 79 |
+
"loss": 0.3909,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.289321409784324,
|
| 84 |
+
"grad_norm": 82.08606719970703,
|
| 85 |
+
"learning_rate": 1.8844818516570228e-05,
|
| 86 |
+
"loss": 0.3945,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3156233561283535,
|
| 91 |
+
"grad_norm": 5.5329389572143555,
|
| 92 |
+
"learning_rate": 1.873961073119411e-05,
|
| 93 |
+
"loss": 0.3182,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.34192530247238295,
|
| 98 |
+
"grad_norm": 10.177448272705078,
|
| 99 |
+
"learning_rate": 1.8634402945817993e-05,
|
| 100 |
+
"loss": 0.3294,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3682272488164124,
|
| 105 |
+
"grad_norm": 11.596871376037598,
|
| 106 |
+
"learning_rate": 1.8529195160441876e-05,
|
| 107 |
+
"loss": 0.3445,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3945291951604419,
|
| 112 |
+
"grad_norm": 5.0095319747924805,
|
| 113 |
+
"learning_rate": 1.8423987375065758e-05,
|
| 114 |
+
"loss": 0.3403,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4208311415044713,
|
| 119 |
+
"grad_norm": 6.569547653198242,
|
| 120 |
+
"learning_rate": 1.8318779589689638e-05,
|
| 121 |
+
"loss": 0.2767,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4471330878485008,
|
| 126 |
+
"grad_norm": 7.269279956817627,
|
| 127 |
+
"learning_rate": 1.821357180431352e-05,
|
| 128 |
+
"loss": 0.3391,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.47343503419253025,
|
| 133 |
+
"grad_norm": 6.403675079345703,
|
| 134 |
+
"learning_rate": 1.8108364018937403e-05,
|
| 135 |
+
"loss": 0.2729,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4997369805365597,
|
| 140 |
+
"grad_norm": 18.03633689880371,
|
| 141 |
+
"learning_rate": 1.8003156233561285e-05,
|
| 142 |
+
"loss": 0.2912,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5260389268805892,
|
| 147 |
+
"grad_norm": 11.609797477722168,
|
| 148 |
+
"learning_rate": 1.7897948448185168e-05,
|
| 149 |
+
"loss": 0.3678,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.5523408732246187,
|
| 154 |
+
"grad_norm": 8.587767601013184,
|
| 155 |
+
"learning_rate": 1.779274066280905e-05,
|
| 156 |
+
"loss": 0.2789,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.578642819568648,
|
| 161 |
+
"grad_norm": 2.894766092300415,
|
| 162 |
+
"learning_rate": 1.768753287743293e-05,
|
| 163 |
+
"loss": 0.2515,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6049447659126775,
|
| 168 |
+
"grad_norm": 14.84619140625,
|
| 169 |
+
"learning_rate": 1.7582325092056812e-05,
|
| 170 |
+
"loss": 0.2817,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.631246712256707,
|
| 175 |
+
"grad_norm": 14.3659029006958,
|
| 176 |
+
"learning_rate": 1.7477117306680695e-05,
|
| 177 |
+
"loss": 0.2819,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6575486586007364,
|
| 182 |
+
"grad_norm": 24.962841033935547,
|
| 183 |
+
"learning_rate": 1.7371909521304578e-05,
|
| 184 |
+
"loss": 0.275,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.6838506049447659,
|
| 189 |
+
"grad_norm": 2.1663622856140137,
|
| 190 |
+
"learning_rate": 1.726670173592846e-05,
|
| 191 |
+
"loss": 0.2513,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.7101525512887954,
|
| 196 |
+
"grad_norm": 20.324939727783203,
|
| 197 |
+
"learning_rate": 1.7161493950552343e-05,
|
| 198 |
+
"loss": 0.2862,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7364544976328248,
|
| 203 |
+
"grad_norm": 12.115033149719238,
|
| 204 |
+
"learning_rate": 1.7056286165176222e-05,
|
| 205 |
+
"loss": 0.2489,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7627564439768543,
|
| 210 |
+
"grad_norm": 9.39247989654541,
|
| 211 |
+
"learning_rate": 1.6951078379800105e-05,
|
| 212 |
+
"loss": 0.2199,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.7890583903208838,
|
| 217 |
+
"grad_norm": 11.820609092712402,
|
| 218 |
+
"learning_rate": 1.684587059442399e-05,
|
| 219 |
+
"loss": 0.2334,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8153603366649133,
|
| 224 |
+
"grad_norm": 5.685638427734375,
|
| 225 |
+
"learning_rate": 1.6740662809047873e-05,
|
| 226 |
+
"loss": 0.2859,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8416622830089426,
|
| 231 |
+
"grad_norm": 1.4263566732406616,
|
| 232 |
+
"learning_rate": 1.6635455023671752e-05,
|
| 233 |
+
"loss": 0.2712,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.8679642293529721,
|
| 238 |
+
"grad_norm": 43.12693786621094,
|
| 239 |
+
"learning_rate": 1.6530247238295635e-05,
|
| 240 |
+
"loss": 0.2236,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.8942661756970016,
|
| 245 |
+
"grad_norm": 18.322067260742188,
|
| 246 |
+
"learning_rate": 1.6425039452919518e-05,
|
| 247 |
+
"loss": 0.2176,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.920568122041031,
|
| 252 |
+
"grad_norm": 8.125885009765625,
|
| 253 |
+
"learning_rate": 1.63198316675434e-05,
|
| 254 |
+
"loss": 0.2344,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.9468700683850605,
|
| 259 |
+
"grad_norm": 4.2774457931518555,
|
| 260 |
+
"learning_rate": 1.6214623882167283e-05,
|
| 261 |
+
"loss": 0.2173,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.97317201472909,
|
| 266 |
+
"grad_norm": 8.311309814453125,
|
| 267 |
+
"learning_rate": 1.6109416096791165e-05,
|
| 268 |
+
"loss": 0.207,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.9994739610731194,
|
| 273 |
+
"grad_norm": 18.770065307617188,
|
| 274 |
+
"learning_rate": 1.6004208311415045e-05,
|
| 275 |
+
"loss": 0.2261,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.0,
|
| 280 |
+
"eval_FPR_aeb_Arab": 0.007114016533913859,
|
| 281 |
+
"eval_FPR_arb_Arab": 0.007306287251046666,
|
| 282 |
+
"eval_FPR_ars_Arab": 0.0274961810821419,
|
| 283 |
+
"eval_FPR_arz_Arab": 0.03769230768505917,
|
| 284 |
+
"eval_accuracy": 0.9382975924220497,
|
| 285 |
+
"eval_loss": 0.2227914035320282,
|
| 286 |
+
"eval_macro_f1": 0.8929982487077235,
|
| 287 |
+
"eval_runtime": 3.3475,
|
| 288 |
+
"eval_samples_per_second": 2270.666,
|
| 289 |
+
"eval_steps_per_second": 35.549,
|
| 290 |
+
"step": 1901
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0257759074171489,
|
| 294 |
+
"grad_norm": 7.249199390411377,
|
| 295 |
+
"learning_rate": 1.5899000526038927e-05,
|
| 296 |
+
"loss": 0.1908,
|
| 297 |
+
"step": 1950
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0520778537611783,
|
| 301 |
+
"grad_norm": 16.18492889404297,
|
| 302 |
+
"learning_rate": 1.579379274066281e-05,
|
| 303 |
+
"loss": 0.1919,
|
| 304 |
+
"step": 2000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0783798001052078,
|
| 308 |
+
"grad_norm": 6.383620262145996,
|
| 309 |
+
"learning_rate": 1.5688584955286692e-05,
|
| 310 |
+
"loss": 0.1662,
|
| 311 |
+
"step": 2050
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.1046817464492373,
|
| 315 |
+
"grad_norm": 2.7821247577667236,
|
| 316 |
+
"learning_rate": 1.5583377169910575e-05,
|
| 317 |
+
"loss": 0.1832,
|
| 318 |
+
"step": 2100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1309836927932668,
|
| 322 |
+
"grad_norm": 0.20694231986999512,
|
| 323 |
+
"learning_rate": 1.5478169384534458e-05,
|
| 324 |
+
"loss": 0.1277,
|
| 325 |
+
"step": 2150
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.157285639137296,
|
| 329 |
+
"grad_norm": 66.66133880615234,
|
| 330 |
+
"learning_rate": 1.5372961599158337e-05,
|
| 331 |
+
"loss": 0.1896,
|
| 332 |
+
"step": 2200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1835875854813256,
|
| 336 |
+
"grad_norm": 5.3264055252075195,
|
| 337 |
+
"learning_rate": 1.526775381378222e-05,
|
| 338 |
+
"loss": 0.1535,
|
| 339 |
+
"step": 2250
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.209889531825355,
|
| 343 |
+
"grad_norm": 3.480900526046753,
|
| 344 |
+
"learning_rate": 1.5162546028406104e-05,
|
| 345 |
+
"loss": 0.1767,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2361914781693846,
|
| 350 |
+
"grad_norm": 2.1541006565093994,
|
| 351 |
+
"learning_rate": 1.5057338243029986e-05,
|
| 352 |
+
"loss": 0.2361,
|
| 353 |
+
"step": 2350
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.262493424513414,
|
| 357 |
+
"grad_norm": 13.037530899047852,
|
| 358 |
+
"learning_rate": 1.4952130457653869e-05,
|
| 359 |
+
"loss": 0.1733,
|
| 360 |
+
"step": 2400
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.2887953708574433,
|
| 364 |
+
"grad_norm": 6.1545281410217285,
|
| 365 |
+
"learning_rate": 1.484692267227775e-05,
|
| 366 |
+
"loss": 0.1608,
|
| 367 |
+
"step": 2450
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3150973172014728,
|
| 371 |
+
"grad_norm": 1.8223601579666138,
|
| 372 |
+
"learning_rate": 1.4741714886901633e-05,
|
| 373 |
+
"loss": 0.1746,
|
| 374 |
+
"step": 2500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3413992635455023,
|
| 378 |
+
"grad_norm": 3.253241777420044,
|
| 379 |
+
"learning_rate": 1.4636507101525515e-05,
|
| 380 |
+
"loss": 0.1466,
|
| 381 |
+
"step": 2550
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3677012098895318,
|
| 385 |
+
"grad_norm": 3.3945982456207275,
|
| 386 |
+
"learning_rate": 1.4531299316149396e-05,
|
| 387 |
+
"loss": 0.1732,
|
| 388 |
+
"step": 2600
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3940031562335613,
|
| 392 |
+
"grad_norm": 6.702133655548096,
|
| 393 |
+
"learning_rate": 1.4426091530773279e-05,
|
| 394 |
+
"loss": 0.2324,
|
| 395 |
+
"step": 2650
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.4203051025775908,
|
| 399 |
+
"grad_norm": 3.2291910648345947,
|
| 400 |
+
"learning_rate": 1.4320883745397161e-05,
|
| 401 |
+
"loss": 0.1615,
|
| 402 |
+
"step": 2700
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4466070489216203,
|
| 406 |
+
"grad_norm": 8.065141677856445,
|
| 407 |
+
"learning_rate": 1.4215675960021042e-05,
|
| 408 |
+
"loss": 0.1668,
|
| 409 |
+
"step": 2750
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.4729089952656498,
|
| 413 |
+
"grad_norm": 8.395434379577637,
|
| 414 |
+
"learning_rate": 1.4110468174644925e-05,
|
| 415 |
+
"loss": 0.2002,
|
| 416 |
+
"step": 2800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.499210941609679,
|
| 420 |
+
"grad_norm": 5.985948085784912,
|
| 421 |
+
"learning_rate": 1.4005260389268807e-05,
|
| 422 |
+
"loss": 0.1338,
|
| 423 |
+
"step": 2850
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.5255128879537085,
|
| 427 |
+
"grad_norm": 4.8504791259765625,
|
| 428 |
+
"learning_rate": 1.3900052603892688e-05,
|
| 429 |
+
"loss": 0.1493,
|
| 430 |
+
"step": 2900
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.551814834297738,
|
| 434 |
+
"grad_norm": 30.86811637878418,
|
| 435 |
+
"learning_rate": 1.3794844818516571e-05,
|
| 436 |
+
"loss": 0.1653,
|
| 437 |
+
"step": 2950
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.5781167806417675,
|
| 441 |
+
"grad_norm": 8.025301933288574,
|
| 442 |
+
"learning_rate": 1.3689637033140453e-05,
|
| 443 |
+
"loss": 0.195,
|
| 444 |
+
"step": 3000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.6044187269857968,
|
| 448 |
+
"grad_norm": 2.7844748497009277,
|
| 449 |
+
"learning_rate": 1.3584429247764334e-05,
|
| 450 |
+
"loss": 0.1513,
|
| 451 |
+
"step": 3050
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.6307206733298263,
|
| 455 |
+
"grad_norm": 15.212594032287598,
|
| 456 |
+
"learning_rate": 1.3479221462388219e-05,
|
| 457 |
+
"loss": 0.1311,
|
| 458 |
+
"step": 3100
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.6570226196738558,
|
| 462 |
+
"grad_norm": 7.984399795532227,
|
| 463 |
+
"learning_rate": 1.3374013677012101e-05,
|
| 464 |
+
"loss": 0.1699,
|
| 465 |
+
"step": 3150
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6833245660178853,
|
| 469 |
+
"grad_norm": 2.66343092918396,
|
| 470 |
+
"learning_rate": 1.3268805891635982e-05,
|
| 471 |
+
"loss": 0.0987,
|
| 472 |
+
"step": 3200
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.7096265123619148,
|
| 476 |
+
"grad_norm": 1.7281841039657593,
|
| 477 |
+
"learning_rate": 1.3163598106259865e-05,
|
| 478 |
+
"loss": 0.1468,
|
| 479 |
+
"step": 3250
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.7359284587059443,
|
| 483 |
+
"grad_norm": 80.2880859375,
|
| 484 |
+
"learning_rate": 1.3058390320883747e-05,
|
| 485 |
+
"loss": 0.1225,
|
| 486 |
+
"step": 3300
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7622304050499737,
|
| 490 |
+
"grad_norm": 3.2839515209198,
|
| 491 |
+
"learning_rate": 1.2953182535507628e-05,
|
| 492 |
+
"loss": 0.1612,
|
| 493 |
+
"step": 3350
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.7885323513940032,
|
| 497 |
+
"grad_norm": 6.35798978805542,
|
| 498 |
+
"learning_rate": 1.2847974750131511e-05,
|
| 499 |
+
"loss": 0.1319,
|
| 500 |
+
"step": 3400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.8148342977380327,
|
| 504 |
+
"grad_norm": 17.910255432128906,
|
| 505 |
+
"learning_rate": 1.2742766964755394e-05,
|
| 506 |
+
"loss": 0.2161,
|
| 507 |
+
"step": 3450
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.8411362440820622,
|
| 511 |
+
"grad_norm": 2.275036573410034,
|
| 512 |
+
"learning_rate": 1.2637559179379274e-05,
|
| 513 |
+
"loss": 0.1118,
|
| 514 |
+
"step": 3500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.8674381904260915,
|
| 518 |
+
"grad_norm": 20.091514587402344,
|
| 519 |
+
"learning_rate": 1.2532351394003157e-05,
|
| 520 |
+
"loss": 0.1463,
|
| 521 |
+
"step": 3550
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.893740136770121,
|
| 525 |
+
"grad_norm": 0.5615454912185669,
|
| 526 |
+
"learning_rate": 1.242714360862704e-05,
|
| 527 |
+
"loss": 0.1648,
|
| 528 |
+
"step": 3600
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.9200420831141505,
|
| 532 |
+
"grad_norm": 3.871091604232788,
|
| 533 |
+
"learning_rate": 1.232193582325092e-05,
|
| 534 |
+
"loss": 0.1325,
|
| 535 |
+
"step": 3650
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.9463440294581797,
|
| 539 |
+
"grad_norm": 1.768117904663086,
|
| 540 |
+
"learning_rate": 1.2216728037874803e-05,
|
| 541 |
+
"loss": 0.1664,
|
| 542 |
+
"step": 3700
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.9726459758022092,
|
| 546 |
+
"grad_norm": 5.8534393310546875,
|
| 547 |
+
"learning_rate": 1.2111520252498686e-05,
|
| 548 |
+
"loss": 0.1578,
|
| 549 |
+
"step": 3750
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.9989479221462387,
|
| 553 |
+
"grad_norm": 3.766312837600708,
|
| 554 |
+
"learning_rate": 1.2006312467122567e-05,
|
| 555 |
+
"loss": 0.1393,
|
| 556 |
+
"step": 3800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.0,
|
| 560 |
+
"eval_FPR_aeb_Arab": 0.00384541434265614,
|
| 561 |
+
"eval_FPR_arb_Arab": 0.02134204960174158,
|
| 562 |
+
"eval_FPR_ars_Arab": 0.01041522010687193,
|
| 563 |
+
"eval_FPR_arz_Arab": 0.020192307688424557,
|
| 564 |
+
"eval_accuracy": 0.9590843310090778,
|
| 565 |
+
"eval_loss": 0.16003794968128204,
|
| 566 |
+
"eval_macro_f1": 0.937683933464698,
|
| 567 |
+
"eval_runtime": 3.3754,
|
| 568 |
+
"eval_samples_per_second": 2251.882,
|
| 569 |
+
"eval_steps_per_second": 35.255,
|
| 570 |
+
"step": 3802
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0252498684902682,
|
| 574 |
+
"grad_norm": 14.620624542236328,
|
| 575 |
+
"learning_rate": 1.190110468174645e-05,
|
| 576 |
+
"loss": 0.073,
|
| 577 |
+
"step": 3850
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.0515518148342977,
|
| 581 |
+
"grad_norm": 1.2938824892044067,
|
| 582 |
+
"learning_rate": 1.1795896896370332e-05,
|
| 583 |
+
"loss": 0.1148,
|
| 584 |
+
"step": 3900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.077853761178327,
|
| 588 |
+
"grad_norm": 3.313081979751587,
|
| 589 |
+
"learning_rate": 1.1690689110994216e-05,
|
| 590 |
+
"loss": 0.0746,
|
| 591 |
+
"step": 3950
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.1041557075223567,
|
| 595 |
+
"grad_norm": 2.0338821411132812,
|
| 596 |
+
"learning_rate": 1.1585481325618097e-05,
|
| 597 |
+
"loss": 0.0977,
|
| 598 |
+
"step": 4000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.130457653866386,
|
| 602 |
+
"grad_norm": 0.055320367217063904,
|
| 603 |
+
"learning_rate": 1.148027354024198e-05,
|
| 604 |
+
"loss": 0.096,
|
| 605 |
+
"step": 4050
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.1567596002104157,
|
| 609 |
+
"grad_norm": 1.0964843034744263,
|
| 610 |
+
"learning_rate": 1.1375065754865862e-05,
|
| 611 |
+
"loss": 0.0642,
|
| 612 |
+
"step": 4100
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.183061546554445,
|
| 616 |
+
"grad_norm": 1.0340650081634521,
|
| 617 |
+
"learning_rate": 1.1269857969489743e-05,
|
| 618 |
+
"loss": 0.1007,
|
| 619 |
+
"step": 4150
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.2093634928984747,
|
| 623 |
+
"grad_norm": 4.971868515014648,
|
| 624 |
+
"learning_rate": 1.1164650184113626e-05,
|
| 625 |
+
"loss": 0.1083,
|
| 626 |
+
"step": 4200
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.2356654392425037,
|
| 630 |
+
"grad_norm": 0.49501538276672363,
|
| 631 |
+
"learning_rate": 1.1059442398737508e-05,
|
| 632 |
+
"loss": 0.1068,
|
| 633 |
+
"step": 4250
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.2619673855865337,
|
| 637 |
+
"grad_norm": 6.13097620010376,
|
| 638 |
+
"learning_rate": 1.095423461336139e-05,
|
| 639 |
+
"loss": 0.0946,
|
| 640 |
+
"step": 4300
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.2882693319305627,
|
| 644 |
+
"grad_norm": 5.904395580291748,
|
| 645 |
+
"learning_rate": 1.0849026827985272e-05,
|
| 646 |
+
"loss": 0.0758,
|
| 647 |
+
"step": 4350
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.314571278274592,
|
| 651 |
+
"grad_norm": 4.2567138671875,
|
| 652 |
+
"learning_rate": 1.0743819042609155e-05,
|
| 653 |
+
"loss": 0.111,
|
| 654 |
+
"step": 4400
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.3408732246186217,
|
| 658 |
+
"grad_norm": 0.1440172791481018,
|
| 659 |
+
"learning_rate": 1.0638611257233035e-05,
|
| 660 |
+
"loss": 0.1104,
|
| 661 |
+
"step": 4450
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.367175170962651,
|
| 665 |
+
"grad_norm": 7.970292091369629,
|
| 666 |
+
"learning_rate": 1.0533403471856918e-05,
|
| 667 |
+
"loss": 0.0891,
|
| 668 |
+
"step": 4500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.3934771173066807,
|
| 672 |
+
"grad_norm": 2.4047350883483887,
|
| 673 |
+
"learning_rate": 1.04281956864808e-05,
|
| 674 |
+
"loss": 0.1242,
|
| 675 |
+
"step": 4550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.41977906365071,
|
| 679 |
+
"grad_norm": 14.3352689743042,
|
| 680 |
+
"learning_rate": 1.0322987901104682e-05,
|
| 681 |
+
"loss": 0.0649,
|
| 682 |
+
"step": 4600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.4460810099947397,
|
| 686 |
+
"grad_norm": 25.1345157623291,
|
| 687 |
+
"learning_rate": 1.0217780115728564e-05,
|
| 688 |
+
"loss": 0.0712,
|
| 689 |
+
"step": 4650
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.472382956338769,
|
| 693 |
+
"grad_norm": 1.9517714977264404,
|
| 694 |
+
"learning_rate": 1.0112572330352445e-05,
|
| 695 |
+
"loss": 0.1032,
|
| 696 |
+
"step": 4700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.4986849026827986,
|
| 700 |
+
"grad_norm": 1.327062726020813,
|
| 701 |
+
"learning_rate": 1.000736454497633e-05,
|
| 702 |
+
"loss": 0.0962,
|
| 703 |
+
"step": 4750
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.524986849026828,
|
| 707 |
+
"grad_norm": 10.327136993408203,
|
| 708 |
+
"learning_rate": 9.90215675960021e-06,
|
| 709 |
+
"loss": 0.1092,
|
| 710 |
+
"step": 4800
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.5512887953708576,
|
| 714 |
+
"grad_norm": 3.8997962474823,
|
| 715 |
+
"learning_rate": 9.796948974224093e-06,
|
| 716 |
+
"loss": 0.0681,
|
| 717 |
+
"step": 4850
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.5775907417148867,
|
| 721 |
+
"grad_norm": 0.270841121673584,
|
| 722 |
+
"learning_rate": 9.691741188847975e-06,
|
| 723 |
+
"loss": 0.1265,
|
| 724 |
+
"step": 4900
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.6038926880589166,
|
| 728 |
+
"grad_norm": 0.8220506906509399,
|
| 729 |
+
"learning_rate": 9.586533403471858e-06,
|
| 730 |
+
"loss": 0.0726,
|
| 731 |
+
"step": 4950
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.6301946344029457,
|
| 735 |
+
"grad_norm": 1.4264813661575317,
|
| 736 |
+
"learning_rate": 9.48132561809574e-06,
|
| 737 |
+
"loss": 0.0707,
|
| 738 |
+
"step": 5000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.656496580746975,
|
| 742 |
+
"grad_norm": 5.427404880523682,
|
| 743 |
+
"learning_rate": 9.376117832719622e-06,
|
| 744 |
+
"loss": 0.0762,
|
| 745 |
+
"step": 5050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.6827985270910046,
|
| 749 |
+
"grad_norm": 39.103004455566406,
|
| 750 |
+
"learning_rate": 9.270910047343504e-06,
|
| 751 |
+
"loss": 0.0733,
|
| 752 |
+
"step": 5100
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.709100473435034,
|
| 756 |
+
"grad_norm": 2.8170275688171387,
|
| 757 |
+
"learning_rate": 9.165702261967387e-06,
|
| 758 |
+
"loss": 0.105,
|
| 759 |
+
"step": 5150
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.7354024197790636,
|
| 763 |
+
"grad_norm": 6.285243034362793,
|
| 764 |
+
"learning_rate": 9.060494476591268e-06,
|
| 765 |
+
"loss": 0.1054,
|
| 766 |
+
"step": 5200
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.761704366123093,
|
| 770 |
+
"grad_norm": 34.959102630615234,
|
| 771 |
+
"learning_rate": 8.95528669121515e-06,
|
| 772 |
+
"loss": 0.1168,
|
| 773 |
+
"step": 5250
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.7880063124671226,
|
| 777 |
+
"grad_norm": 2.698047399520874,
|
| 778 |
+
"learning_rate": 8.850078905839033e-06,
|
| 779 |
+
"loss": 0.0664,
|
| 780 |
+
"step": 5300
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.814308258811152,
|
| 784 |
+
"grad_norm": 6.107056617736816,
|
| 785 |
+
"learning_rate": 8.744871120462914e-06,
|
| 786 |
+
"loss": 0.0866,
|
| 787 |
+
"step": 5350
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.8406102051551816,
|
| 791 |
+
"grad_norm": 6.0492634773254395,
|
| 792 |
+
"learning_rate": 8.639663335086798e-06,
|
| 793 |
+
"loss": 0.0921,
|
| 794 |
+
"step": 5400
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.866912151499211,
|
| 798 |
+
"grad_norm": 38.75687789916992,
|
| 799 |
+
"learning_rate": 8.534455549710679e-06,
|
| 800 |
+
"loss": 0.0932,
|
| 801 |
+
"step": 5450
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.8932140978432406,
|
| 805 |
+
"grad_norm": 5.730583190917969,
|
| 806 |
+
"learning_rate": 8.429247764334562e-06,
|
| 807 |
+
"loss": 0.0809,
|
| 808 |
+
"step": 5500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.9195160441872696,
|
| 812 |
+
"grad_norm": 0.2023005187511444,
|
| 813 |
+
"learning_rate": 8.324039978958444e-06,
|
| 814 |
+
"loss": 0.0723,
|
| 815 |
+
"step": 5550
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.9458179905312996,
|
| 819 |
+
"grad_norm": 24.816850662231445,
|
| 820 |
+
"learning_rate": 8.218832193582325e-06,
|
| 821 |
+
"loss": 0.0758,
|
| 822 |
+
"step": 5600
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.9721199368753286,
|
| 826 |
+
"grad_norm": 0.10021505504846573,
|
| 827 |
+
"learning_rate": 8.113624408206208e-06,
|
| 828 |
+
"loss": 0.0787,
|
| 829 |
+
"step": 5650
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.998421883219358,
|
| 833 |
+
"grad_norm": 3.8389430046081543,
|
| 834 |
+
"learning_rate": 8.00841662283009e-06,
|
| 835 |
+
"loss": 0.1321,
|
| 836 |
+
"step": 5700
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.0,
|
| 840 |
+
"eval_FPR_aeb_Arab": 0.004037685059788947,
|
| 841 |
+
"eval_FPR_arb_Arab": 0.009421265139507543,
|
| 842 |
+
"eval_FPR_ars_Arab": 0.005971392861273241,
|
| 843 |
+
"eval_FPR_arz_Arab": 0.020192307688424557,
|
| 844 |
+
"eval_accuracy": 0.9713195632153664,
|
| 845 |
+
"eval_loss": 0.15336963534355164,
|
| 846 |
+
"eval_macro_f1": 0.9569564393242584,
|
| 847 |
+
"eval_runtime": 3.3689,
|
| 848 |
+
"eval_samples_per_second": 2256.259,
|
| 849 |
+
"eval_steps_per_second": 35.324,
|
| 850 |
+
"step": 5703
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 3.0247238295633876,
|
| 854 |
+
"grad_norm": 0.30554988980293274,
|
| 855 |
+
"learning_rate": 7.903208837453971e-06,
|
| 856 |
+
"loss": 0.0937,
|
| 857 |
+
"step": 5750
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.051025775907417,
|
| 861 |
+
"grad_norm": 37.439884185791016,
|
| 862 |
+
"learning_rate": 7.798001052077856e-06,
|
| 863 |
+
"loss": 0.0578,
|
| 864 |
+
"step": 5800
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.0773277222514466,
|
| 868 |
+
"grad_norm": 0.0822492390871048,
|
| 869 |
+
"learning_rate": 7.692793266701737e-06,
|
| 870 |
+
"loss": 0.0636,
|
| 871 |
+
"step": 5850
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.103629668595476,
|
| 875 |
+
"grad_norm": 2.7918007373809814,
|
| 876 |
+
"learning_rate": 7.587585481325619e-06,
|
| 877 |
+
"loss": 0.0378,
|
| 878 |
+
"step": 5900
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.1299316149395056,
|
| 882 |
+
"grad_norm": 32.899818420410156,
|
| 883 |
+
"learning_rate": 7.482377695949501e-06,
|
| 884 |
+
"loss": 0.0609,
|
| 885 |
+
"step": 5950
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.156233561283535,
|
| 889 |
+
"grad_norm": 0.06830895692110062,
|
| 890 |
+
"learning_rate": 7.377169910573383e-06,
|
| 891 |
+
"loss": 0.0433,
|
| 892 |
+
"step": 6000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.1825355076275645,
|
| 896 |
+
"grad_norm": 54.685489654541016,
|
| 897 |
+
"learning_rate": 7.271962125197265e-06,
|
| 898 |
+
"loss": 0.056,
|
| 899 |
+
"step": 6050
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.208837453971594,
|
| 903 |
+
"grad_norm": 0.8175523281097412,
|
| 904 |
+
"learning_rate": 7.166754339821147e-06,
|
| 905 |
+
"loss": 0.0341,
|
| 906 |
+
"step": 6100
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.2351394003156235,
|
| 910 |
+
"grad_norm": 0.33226722478866577,
|
| 911 |
+
"learning_rate": 7.061546554445029e-06,
|
| 912 |
+
"loss": 0.0482,
|
| 913 |
+
"step": 6150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.2614413466596526,
|
| 917 |
+
"grad_norm": 1.425661325454712,
|
| 918 |
+
"learning_rate": 6.956338769068912e-06,
|
| 919 |
+
"loss": 0.0673,
|
| 920 |
+
"step": 6200
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.2877432930036825,
|
| 924 |
+
"grad_norm": 0.18895921111106873,
|
| 925 |
+
"learning_rate": 6.851130983692794e-06,
|
| 926 |
+
"loss": 0.0359,
|
| 927 |
+
"step": 6250
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.3140452393477116,
|
| 931 |
+
"grad_norm": 0.6557305455207825,
|
| 932 |
+
"learning_rate": 6.7459231983166766e-06,
|
| 933 |
+
"loss": 0.0382,
|
| 934 |
+
"step": 6300
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.340347185691741,
|
| 938 |
+
"grad_norm": 0.008198770694434643,
|
| 939 |
+
"learning_rate": 6.640715412940558e-06,
|
| 940 |
+
"loss": 0.0566,
|
| 941 |
+
"step": 6350
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.3666491320357705,
|
| 945 |
+
"grad_norm": 0.4695976674556732,
|
| 946 |
+
"learning_rate": 6.53550762756444e-06,
|
| 947 |
+
"loss": 0.0654,
|
| 948 |
+
"step": 6400
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.3929510783798,
|
| 952 |
+
"grad_norm": 8.628214836120605,
|
| 953 |
+
"learning_rate": 6.430299842188323e-06,
|
| 954 |
+
"loss": 0.0427,
|
| 955 |
+
"step": 6450
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.4192530247238295,
|
| 959 |
+
"grad_norm": 0.9650713801383972,
|
| 960 |
+
"learning_rate": 6.3250920568122044e-06,
|
| 961 |
+
"loss": 0.0645,
|
| 962 |
+
"step": 6500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 3.445554971067859,
|
| 966 |
+
"grad_norm": 5.836668968200684,
|
| 967 |
+
"learning_rate": 6.219884271436086e-06,
|
| 968 |
+
"loss": 0.0397,
|
| 969 |
+
"step": 6550
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.4718569174118885,
|
| 973 |
+
"grad_norm": 0.03976545110344887,
|
| 974 |
+
"learning_rate": 6.11467648605997e-06,
|
| 975 |
+
"loss": 0.0586,
|
| 976 |
+
"step": 6600
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.498158863755918,
|
| 980 |
+
"grad_norm": 19.784215927124023,
|
| 981 |
+
"learning_rate": 6.009468700683851e-06,
|
| 982 |
+
"loss": 0.033,
|
| 983 |
+
"step": 6650
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.5244608100999475,
|
| 987 |
+
"grad_norm": 2.075496196746826,
|
| 988 |
+
"learning_rate": 5.904260915307733e-06,
|
| 989 |
+
"loss": 0.0776,
|
| 990 |
+
"step": 6700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 3.550762756443977,
|
| 994 |
+
"grad_norm": 7.05810022354126,
|
| 995 |
+
"learning_rate": 5.799053129931616e-06,
|
| 996 |
+
"loss": 0.0905,
|
| 997 |
+
"step": 6750
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 3.5770647027880065,
|
| 1001 |
+
"grad_norm": 0.012984913773834705,
|
| 1002 |
+
"learning_rate": 5.6938453445554975e-06,
|
| 1003 |
+
"loss": 0.0542,
|
| 1004 |
+
"step": 6800
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.6033666491320355,
|
| 1008 |
+
"grad_norm": 2.701481342315674,
|
| 1009 |
+
"learning_rate": 5.588637559179379e-06,
|
| 1010 |
+
"loss": 0.0625,
|
| 1011 |
+
"step": 6850
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 3.6296685954760655,
|
| 1015 |
+
"grad_norm": 0.41872379183769226,
|
| 1016 |
+
"learning_rate": 5.483429773803262e-06,
|
| 1017 |
+
"loss": 0.0795,
|
| 1018 |
+
"step": 6900
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 3.6559705418200945,
|
| 1022 |
+
"grad_norm": 0.13123294711112976,
|
| 1023 |
+
"learning_rate": 5.378221988427144e-06,
|
| 1024 |
+
"loss": 0.0296,
|
| 1025 |
+
"step": 6950
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.682272488164124,
|
| 1029 |
+
"grad_norm": 0.7190969586372375,
|
| 1030 |
+
"learning_rate": 5.273014203051027e-06,
|
| 1031 |
+
"loss": 0.0666,
|
| 1032 |
+
"step": 7000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 3.7085744345081535,
|
| 1036 |
+
"grad_norm": 0.1744261384010315,
|
| 1037 |
+
"learning_rate": 5.167806417674909e-06,
|
| 1038 |
+
"loss": 0.0328,
|
| 1039 |
+
"step": 7050
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 3.734876380852183,
|
| 1043 |
+
"grad_norm": 0.5619340538978577,
|
| 1044 |
+
"learning_rate": 5.062598632298791e-06,
|
| 1045 |
+
"loss": 0.0755,
|
| 1046 |
+
"step": 7100
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.7611783271962125,
|
| 1050 |
+
"grad_norm": 40.665706634521484,
|
| 1051 |
+
"learning_rate": 4.957390846922673e-06,
|
| 1052 |
+
"loss": 0.1041,
|
| 1053 |
+
"step": 7150
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 3.787480273540242,
|
| 1057 |
+
"grad_norm": 0.06617475301027298,
|
| 1058 |
+
"learning_rate": 4.852183061546555e-06,
|
| 1059 |
+
"loss": 0.0264,
|
| 1060 |
+
"step": 7200
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 3.8137822198842715,
|
| 1064 |
+
"grad_norm": 5.0283966064453125,
|
| 1065 |
+
"learning_rate": 4.746975276170437e-06,
|
| 1066 |
+
"loss": 0.0789,
|
| 1067 |
+
"step": 7250
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 3.840084166228301,
|
| 1071 |
+
"grad_norm": 5.660898208618164,
|
| 1072 |
+
"learning_rate": 4.641767490794319e-06,
|
| 1073 |
+
"loss": 0.0582,
|
| 1074 |
+
"step": 7300
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.8663861125723304,
|
| 1078 |
+
"grad_norm": 0.8503484725952148,
|
| 1079 |
+
"learning_rate": 4.536559705418201e-06,
|
| 1080 |
+
"loss": 0.0862,
|
| 1081 |
+
"step": 7350
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 3.89268805891636,
|
| 1085 |
+
"grad_norm": 13.575056076049805,
|
| 1086 |
+
"learning_rate": 4.431351920042084e-06,
|
| 1087 |
+
"loss": 0.0554,
|
| 1088 |
+
"step": 7400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.9189900052603894,
|
| 1092 |
+
"grad_norm": 0.25003504753112793,
|
| 1093 |
+
"learning_rate": 4.3261441346659654e-06,
|
| 1094 |
+
"loss": 0.0504,
|
| 1095 |
+
"step": 7450
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 3.9452919516044185,
|
| 1099 |
+
"grad_norm": 0.022247493267059326,
|
| 1100 |
+
"learning_rate": 4.220936349289847e-06,
|
| 1101 |
+
"loss": 0.0663,
|
| 1102 |
+
"step": 7500
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.9715938979484484,
|
| 1106 |
+
"grad_norm": 0.2591884136199951,
|
| 1107 |
+
"learning_rate": 4.11572856391373e-06,
|
| 1108 |
+
"loss": 0.0361,
|
| 1109 |
+
"step": 7550
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.9978958442924775,
|
| 1113 |
+
"grad_norm": 6.533713340759277,
|
| 1114 |
+
"learning_rate": 4.010520778537612e-06,
|
| 1115 |
+
"loss": 0.0293,
|
| 1116 |
+
"step": 7600
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.0,
|
| 1120 |
+
"eval_FPR_aeb_Arab": 0.004229955776921754,
|
| 1121 |
+
"eval_FPR_arb_Arab": 0.011343972310835613,
|
| 1122 |
+
"eval_FPR_ars_Arab": 0.00458269684702365,
|
| 1123 |
+
"eval_FPR_arz_Arab": 0.015576923073927515,
|
| 1124 |
+
"eval_accuracy": 0.9743454808577818,
|
| 1125 |
+
"eval_loss": 0.15085552632808685,
|
| 1126 |
+
"eval_macro_f1": 0.9633717243752477,
|
| 1127 |
+
"eval_runtime": 3.3689,
|
| 1128 |
+
"eval_samples_per_second": 2256.225,
|
| 1129 |
+
"eval_steps_per_second": 35.323,
|
| 1130 |
+
"step": 7604
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.024197790636507,
|
| 1134 |
+
"grad_norm": 2.82965087890625,
|
| 1135 |
+
"learning_rate": 3.905312993161494e-06,
|
| 1136 |
+
"loss": 0.0275,
|
| 1137 |
+
"step": 7650
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.0504997369805364,
|
| 1141 |
+
"grad_norm": 0.05096087604761124,
|
| 1142 |
+
"learning_rate": 3.8001052077853763e-06,
|
| 1143 |
+
"loss": 0.0334,
|
| 1144 |
+
"step": 7700
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 4.076801683324566,
|
| 1148 |
+
"grad_norm": 0.017893170937895775,
|
| 1149 |
+
"learning_rate": 3.694897422409259e-06,
|
| 1150 |
+
"loss": 0.0435,
|
| 1151 |
+
"step": 7750
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 4.103103629668595,
|
| 1155 |
+
"grad_norm": 0.43649783730506897,
|
| 1156 |
+
"learning_rate": 3.5896896370331407e-06,
|
| 1157 |
+
"loss": 0.0297,
|
| 1158 |
+
"step": 7800
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.1294055760126245,
|
| 1162 |
+
"grad_norm": 0.1193922609090805,
|
| 1163 |
+
"learning_rate": 3.484481851657023e-06,
|
| 1164 |
+
"loss": 0.0308,
|
| 1165 |
+
"step": 7850
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 4.155707522356654,
|
| 1169 |
+
"grad_norm": 0.029588880017399788,
|
| 1170 |
+
"learning_rate": 3.3792740662809046e-06,
|
| 1171 |
+
"loss": 0.0338,
|
| 1172 |
+
"step": 7900
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.1820094687006835,
|
| 1176 |
+
"grad_norm": 9.658980369567871,
|
| 1177 |
+
"learning_rate": 3.2740662809047872e-06,
|
| 1178 |
+
"loss": 0.0431,
|
| 1179 |
+
"step": 7950
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 4.208311415044713,
|
| 1183 |
+
"grad_norm": 0.018898559734225273,
|
| 1184 |
+
"learning_rate": 3.1688584955286694e-06,
|
| 1185 |
+
"loss": 0.0436,
|
| 1186 |
+
"step": 8000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 4.2346133613887424,
|
| 1190 |
+
"grad_norm": 0.33016514778137207,
|
| 1191 |
+
"learning_rate": 3.0636507101525516e-06,
|
| 1192 |
+
"loss": 0.0103,
|
| 1193 |
+
"step": 8050
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.260915307732772,
|
| 1197 |
+
"grad_norm": 4.2456583976745605,
|
| 1198 |
+
"learning_rate": 2.9584429247764334e-06,
|
| 1199 |
+
"loss": 0.0234,
|
| 1200 |
+
"step": 8100
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.287217254076801,
|
| 1204 |
+
"grad_norm": 7.066432476043701,
|
| 1205 |
+
"learning_rate": 2.853235139400316e-06,
|
| 1206 |
+
"loss": 0.0267,
|
| 1207 |
+
"step": 8150
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 4.313519200420831,
|
| 1211 |
+
"grad_norm": 0.010746636427938938,
|
| 1212 |
+
"learning_rate": 2.748027354024198e-06,
|
| 1213 |
+
"loss": 0.0257,
|
| 1214 |
+
"step": 8200
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.33982114676486,
|
| 1218 |
+
"grad_norm": 0.03323914483189583,
|
| 1219 |
+
"learning_rate": 2.64281956864808e-06,
|
| 1220 |
+
"loss": 0.0515,
|
| 1221 |
+
"step": 8250
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 4.36612309310889,
|
| 1225 |
+
"grad_norm": 0.2795711159706116,
|
| 1226 |
+
"learning_rate": 2.537611783271962e-06,
|
| 1227 |
+
"loss": 0.0489,
|
| 1228 |
+
"step": 8300
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 4.392425039452919,
|
| 1232 |
+
"grad_norm": 9.179369926452637,
|
| 1233 |
+
"learning_rate": 2.4324039978958443e-06,
|
| 1234 |
+
"loss": 0.0339,
|
| 1235 |
+
"step": 8350
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 4.418726985796949,
|
| 1239 |
+
"grad_norm": 3.0741329193115234,
|
| 1240 |
+
"learning_rate": 2.327196212519727e-06,
|
| 1241 |
+
"loss": 0.0203,
|
| 1242 |
+
"step": 8400
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 4.445028932140978,
|
| 1246 |
+
"grad_norm": 21.926807403564453,
|
| 1247 |
+
"learning_rate": 2.2219884271436086e-06,
|
| 1248 |
+
"loss": 0.0481,
|
| 1249 |
+
"step": 8450
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 4.471330878485007,
|
| 1253 |
+
"grad_norm": 1.929383635520935,
|
| 1254 |
+
"learning_rate": 2.1167806417674912e-06,
|
| 1255 |
+
"loss": 0.0231,
|
| 1256 |
+
"step": 8500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.497632824829037,
|
| 1260 |
+
"grad_norm": 4.422601699829102,
|
| 1261 |
+
"learning_rate": 2.011572856391373e-06,
|
| 1262 |
+
"loss": 0.034,
|
| 1263 |
+
"step": 8550
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 4.523934771173067,
|
| 1267 |
+
"grad_norm": 0.010013488121330738,
|
| 1268 |
+
"learning_rate": 1.9063650710152554e-06,
|
| 1269 |
+
"loss": 0.0114,
|
| 1270 |
+
"step": 8600
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 4.550236717517096,
|
| 1274 |
+
"grad_norm": 0.002675453433766961,
|
| 1275 |
+
"learning_rate": 1.8011572856391374e-06,
|
| 1276 |
+
"loss": 0.0575,
|
| 1277 |
+
"step": 8650
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 4.576538663861125,
|
| 1281 |
+
"grad_norm": 0.04695653170347214,
|
| 1282 |
+
"learning_rate": 1.6959495002630197e-06,
|
| 1283 |
+
"loss": 0.0419,
|
| 1284 |
+
"step": 8700
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 4.602840610205155,
|
| 1288 |
+
"grad_norm": 0.005277259275317192,
|
| 1289 |
+
"learning_rate": 1.5907417148869017e-06,
|
| 1290 |
+
"loss": 0.0465,
|
| 1291 |
+
"step": 8750
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 4.629142556549184,
|
| 1295 |
+
"grad_norm": 0.03051823005080223,
|
| 1296 |
+
"learning_rate": 1.4855339295107841e-06,
|
| 1297 |
+
"loss": 0.0494,
|
| 1298 |
+
"step": 8800
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.655444502893214,
|
| 1302 |
+
"grad_norm": 0.03725295141339302,
|
| 1303 |
+
"learning_rate": 1.380326144134666e-06,
|
| 1304 |
+
"loss": 0.0279,
|
| 1305 |
+
"step": 8850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 4.681746449237243,
|
| 1309 |
+
"grad_norm": 9.204965591430664,
|
| 1310 |
+
"learning_rate": 1.2751183587585483e-06,
|
| 1311 |
+
"loss": 0.0421,
|
| 1312 |
+
"step": 8900
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 4.708048395581273,
|
| 1316 |
+
"grad_norm": 0.6778242588043213,
|
| 1317 |
+
"learning_rate": 1.1699105733824304e-06,
|
| 1318 |
+
"loss": 0.0275,
|
| 1319 |
+
"step": 8950
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 4.734350341925302,
|
| 1323 |
+
"grad_norm": 0.02842475101351738,
|
| 1324 |
+
"learning_rate": 1.0647027880063126e-06,
|
| 1325 |
+
"loss": 0.0312,
|
| 1326 |
+
"step": 9000
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 4.760652288269332,
|
| 1330 |
+
"grad_norm": 0.03680500015616417,
|
| 1331 |
+
"learning_rate": 9.594950026301946e-07,
|
| 1332 |
+
"loss": 0.0349,
|
| 1333 |
+
"step": 9050
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 4.786954234613361,
|
| 1337 |
+
"grad_norm": 0.4056846797466278,
|
| 1338 |
+
"learning_rate": 8.542872172540769e-07,
|
| 1339 |
+
"loss": 0.0473,
|
| 1340 |
+
"step": 9100
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 4.81325618095739,
|
| 1344 |
+
"grad_norm": 0.005888829007744789,
|
| 1345 |
+
"learning_rate": 7.490794318779591e-07,
|
| 1346 |
+
"loss": 0.0418,
|
| 1347 |
+
"step": 9150
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 4.83955812730142,
|
| 1351 |
+
"grad_norm": 1.9934979677200317,
|
| 1352 |
+
"learning_rate": 6.438716465018411e-07,
|
| 1353 |
+
"loss": 0.0282,
|
| 1354 |
+
"step": 9200
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 4.86586007364545,
|
| 1358 |
+
"grad_norm": 2.1665430068969727,
|
| 1359 |
+
"learning_rate": 5.386638611257233e-07,
|
| 1360 |
+
"loss": 0.0303,
|
| 1361 |
+
"step": 9250
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 4.892162019989479,
|
| 1365 |
+
"grad_norm": 0.07777859270572662,
|
| 1366 |
+
"learning_rate": 4.334560757496055e-07,
|
| 1367 |
+
"loss": 0.0385,
|
| 1368 |
+
"step": 9300
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 4.918463966333508,
|
| 1372 |
+
"grad_norm": 0.1822308897972107,
|
| 1373 |
+
"learning_rate": 3.2824829037348767e-07,
|
| 1374 |
+
"loss": 0.062,
|
| 1375 |
+
"step": 9350
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 4.944765912677538,
|
| 1379 |
+
"grad_norm": 0.13670164346694946,
|
| 1380 |
+
"learning_rate": 2.2304050499736983e-07,
|
| 1381 |
+
"loss": 0.0187,
|
| 1382 |
+
"step": 9400
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 4.971067859021567,
|
| 1386 |
+
"grad_norm": 0.0051955850794911385,
|
| 1387 |
+
"learning_rate": 1.1783271962125198e-07,
|
| 1388 |
+
"loss": 0.0421,
|
| 1389 |
+
"step": 9450
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 4.997369805365597,
|
| 1393 |
+
"grad_norm": 0.008878646418452263,
|
| 1394 |
+
"learning_rate": 1.262493424513414e-08,
|
| 1395 |
+
"loss": 0.0477,
|
| 1396 |
+
"step": 9500
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 5.0,
|
| 1400 |
+
"eval_FPR_aeb_Arab": 0.00384541434265614,
|
| 1401 |
+
"eval_FPR_arb_Arab": 0.011728513745101227,
|
| 1402 |
+
"eval_FPR_ars_Arab": 0.004721566448448609,
|
| 1403 |
+
"eval_FPR_arz_Arab": 0.013461538458949703,
|
| 1404 |
+
"eval_accuracy": 0.9756610972240495,
|
| 1405 |
+
"eval_loss": 0.15560674667358398,
|
| 1406 |
+
"eval_macro_f1": 0.9641750099415428,
|
| 1407 |
+
"eval_runtime": 3.3579,
|
| 1408 |
+
"eval_samples_per_second": 2263.594,
|
| 1409 |
+
"eval_steps_per_second": 35.438,
|
| 1410 |
+
"step": 9505
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 50,
|
| 1414 |
+
"max_steps": 9505,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 5,
|
| 1417 |
+
"save_steps": 500,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"EarlyStoppingCallback": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"early_stopping_patience": 2,
|
| 1422 |
+
"early_stopping_threshold": 0.0
|
| 1423 |
+
},
|
| 1424 |
+
"attributes": {
|
| 1425 |
+
"early_stopping_patience_counter": 0
|
| 1426 |
+
}
|
| 1427 |
+
},
|
| 1428 |
+
"TrainerControl": {
|
| 1429 |
+
"args": {
|
| 1430 |
+
"should_epoch_stop": false,
|
| 1431 |
+
"should_evaluate": false,
|
| 1432 |
+
"should_log": false,
|
| 1433 |
+
"should_save": true,
|
| 1434 |
+
"should_training_stop": true
|
| 1435 |
+
},
|
| 1436 |
+
"attributes": {}
|
| 1437 |
+
}
|
| 1438 |
+
},
|
| 1439 |
+
"total_flos": 4298818504680960.0,
|
| 1440 |
+
"train_batch_size": 32,
|
| 1441 |
+
"trial_name": null,
|
| 1442 |
+
"trial_params": null
|
| 1443 |
+
}
|
checkpoint-9505/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa873479846449ff86b2d50d9e57056c48f72d07a9ffc1fb7f0012ac7d884f8
|
| 3 |
+
size 5777
|
checkpoint-9505/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
confusion_matrix_val.csv
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
,aeb_Arab,arb_Arab,ars_Arab,arz_Arab
|
| 2 |
+
aeb_Arab,2345,15,7,33
|
| 3 |
+
arb_Arab,6,2352,17,25
|
| 4 |
+
ars_Arab,3,15,370,12
|
| 5 |
+
arz_Arab,11,31,10,2349
|
metrics.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{'eval_loss': 0.15560674667358398, 'eval_accuracy': 0.9756610972240495, 'eval_macro_f1': 0.9641750099415428, 'eval_FPR_aeb_Arab': 0.00384541434265614, 'eval_FPR_arb_Arab': 0.011728513745101227, 'eval_FPR_ars_Arab': 0.004721566448448609, 'eval_FPR_arz_Arab': 0.013461538458949703, 'eval_runtime': 3.397, 'eval_samples_per_second': 2237.548, 'eval_steps_per_second': 35.031, 'epoch': 5.0}
|
val_predictions.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|