Upload folder using huggingface_hub
Browse files- best/added_tokens.json +3 -0
- best/config.json +44 -0
- best/model.safetensors +3 -0
- best/special_tokens_map.json +15 -0
- best/spm.model +3 -0
- best/tokenizer.json +0 -0
- best/tokenizer_config.json +59 -0
- best/training_args.bin +3 -0
- checkpoint-11976/added_tokens.json +3 -0
- checkpoint-11976/config.json +44 -0
- checkpoint-11976/model.safetensors +3 -0
- checkpoint-11976/optimizer.pt +3 -0
- checkpoint-11976/rng_state.pth +3 -0
- checkpoint-11976/scheduler.pt +3 -0
- checkpoint-11976/special_tokens_map.json +15 -0
- checkpoint-11976/spm.model +3 -0
- checkpoint-11976/tokenizer.json +0 -0
- checkpoint-11976/tokenizer_config.json +59 -0
- checkpoint-11976/trainer_state.json +212 -0
- checkpoint-11976/training_args.bin +3 -0
- checkpoint-5988/added_tokens.json +3 -0
- checkpoint-5988/config.json +44 -0
- checkpoint-5988/model.safetensors +3 -0
- checkpoint-5988/optimizer.pt +3 -0
- checkpoint-5988/rng_state.pth +3 -0
- checkpoint-5988/scheduler.pt +3 -0
- checkpoint-5988/special_tokens_map.json +15 -0
- checkpoint-5988/spm.model +3 -0
- checkpoint-5988/tokenizer.json +0 -0
- checkpoint-5988/tokenizer_config.json +59 -0
- checkpoint-5988/trainer_state.json +119 -0
- checkpoint-5988/training_args.bin +3 -0
best/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
best/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-xsmall",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 384,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "human",
|
| 12 |
+
"1": "machine"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 1536,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"human": 0,
|
| 18 |
+
"machine": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-07,
|
| 21 |
+
"legacy": true,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"max_relative_positions": -1,
|
| 24 |
+
"model_type": "deberta-v2",
|
| 25 |
+
"norm_rel_ebd": "layer_norm",
|
| 26 |
+
"num_attention_heads": 6,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_dropout": 0,
|
| 30 |
+
"pooler_hidden_act": "gelu",
|
| 31 |
+
"pooler_hidden_size": 384,
|
| 32 |
+
"pos_att_type": [
|
| 33 |
+
"p2c",
|
| 34 |
+
"c2p"
|
| 35 |
+
],
|
| 36 |
+
"position_biased_input": false,
|
| 37 |
+
"position_buckets": 256,
|
| 38 |
+
"relative_attention": true,
|
| 39 |
+
"share_att_key": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.47.0",
|
| 42 |
+
"type_vocab_size": 0,
|
| 43 |
+
"vocab_size": 128100
|
| 44 |
+
}
|
best/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c1b6f5ea2d039b9c9110ade1870be063c10a70afd28849aeaae6c02305d2e0
|
| 3 |
+
size 283347432
|
best/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
best/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
best/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
best/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": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
best/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:789de4a2b6c30e6874a2920b354aec1ad5e4e55abf36678e20075927918410a2
|
| 3 |
+
size 5368
|
checkpoint-11976/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-11976/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-xsmall",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 384,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "human",
|
| 12 |
+
"1": "machine"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 1536,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"human": 0,
|
| 18 |
+
"machine": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-07,
|
| 21 |
+
"legacy": true,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"max_relative_positions": -1,
|
| 24 |
+
"model_type": "deberta-v2",
|
| 25 |
+
"norm_rel_ebd": "layer_norm",
|
| 26 |
+
"num_attention_heads": 6,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_dropout": 0,
|
| 30 |
+
"pooler_hidden_act": "gelu",
|
| 31 |
+
"pooler_hidden_size": 384,
|
| 32 |
+
"pos_att_type": [
|
| 33 |
+
"p2c",
|
| 34 |
+
"c2p"
|
| 35 |
+
],
|
| 36 |
+
"position_biased_input": false,
|
| 37 |
+
"position_buckets": 256,
|
| 38 |
+
"relative_attention": true,
|
| 39 |
+
"share_att_key": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.47.0",
|
| 42 |
+
"type_vocab_size": 0,
|
| 43 |
+
"vocab_size": 128100
|
| 44 |
+
}
|
checkpoint-11976/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02b8f1dc9666c87c99b057b626ec546333ece50dc2c2726116a5c4f02f381bac
|
| 3 |
+
size 283347432
|
checkpoint-11976/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f0f2088cce71a33a60bf9a49c06ae7a59c134d78e12991040e4cc5e61f79a2a
|
| 3 |
+
size 566814714
|
checkpoint-11976/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed57eb25c2204d38611cd294c889cb94217b91fb554d21998d996221e29501e8
|
| 3 |
+
size 14244
|
checkpoint-11976/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28dd990fb8bcb8c54e47457d67281f1cfa14ff9e49d69616761dac732dd545f1
|
| 3 |
+
size 1064
|
checkpoint-11976/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-11976/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-11976/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11976/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": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
checkpoint-11976/trainer_state.json
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2785227596759796,
|
| 3 |
+
"best_model_checkpoint": "Machine-Generated-Text-Detection/deberta/checkpoint-5988",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11976,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08350033400133601,
|
| 13 |
+
"grad_norm": 1.8728934526443481,
|
| 14 |
+
"learning_rate": 1.9164996659986642e-05,
|
| 15 |
+
"loss": 0.2671,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16700066800267202,
|
| 20 |
+
"grad_norm": 0.5576282143592834,
|
| 21 |
+
"learning_rate": 1.832999331997328e-05,
|
| 22 |
+
"loss": 0.1527,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.250501002004008,
|
| 27 |
+
"grad_norm": 7.88850736618042,
|
| 28 |
+
"learning_rate": 1.7494989979959922e-05,
|
| 29 |
+
"loss": 0.135,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33400133600534404,
|
| 34 |
+
"grad_norm": 0.6910138130187988,
|
| 35 |
+
"learning_rate": 1.6659986639946563e-05,
|
| 36 |
+
"loss": 0.1107,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.41750167000668004,
|
| 41 |
+
"grad_norm": 8.903568267822266,
|
| 42 |
+
"learning_rate": 1.58249832999332e-05,
|
| 43 |
+
"loss": 0.1152,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.501002004008016,
|
| 48 |
+
"grad_norm": 0.08548898249864578,
|
| 49 |
+
"learning_rate": 1.498997995991984e-05,
|
| 50 |
+
"loss": 0.1024,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.584502338009352,
|
| 55 |
+
"grad_norm": 8.673635482788086,
|
| 56 |
+
"learning_rate": 1.415497661990648e-05,
|
| 57 |
+
"loss": 0.0967,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6680026720106881,
|
| 62 |
+
"grad_norm": 7.020376682281494,
|
| 63 |
+
"learning_rate": 1.331997327989312e-05,
|
| 64 |
+
"loss": 0.1024,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.751503006012024,
|
| 69 |
+
"grad_norm": 11.58995532989502,
|
| 70 |
+
"learning_rate": 1.248496993987976e-05,
|
| 71 |
+
"loss": 0.0809,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8350033400133601,
|
| 76 |
+
"grad_norm": 8.78143310546875,
|
| 77 |
+
"learning_rate": 1.16499665998664e-05,
|
| 78 |
+
"loss": 0.0823,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.918503674014696,
|
| 83 |
+
"grad_norm": 9.562505722045898,
|
| 84 |
+
"learning_rate": 1.081496325985304e-05,
|
| 85 |
+
"loss": 0.0769,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_f1": 0.9371242484969939,
|
| 91 |
+
"eval_loss": 0.2785227596759796,
|
| 92 |
+
"eval_runtime": 269.2073,
|
| 93 |
+
"eval_samples_per_second": 88.972,
|
| 94 |
+
"eval_steps_per_second": 5.561,
|
| 95 |
+
"step": 5988
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.002004008016032,
|
| 99 |
+
"grad_norm": 9.97668170928955,
|
| 100 |
+
"learning_rate": 9.97995991983968e-06,
|
| 101 |
+
"loss": 0.0756,
|
| 102 |
+
"step": 6000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.085504342017368,
|
| 106 |
+
"grad_norm": 0.9769249558448792,
|
| 107 |
+
"learning_rate": 9.14495657982632e-06,
|
| 108 |
+
"loss": 0.0652,
|
| 109 |
+
"step": 6500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.169004676018704,
|
| 113 |
+
"grad_norm": 0.14497636258602142,
|
| 114 |
+
"learning_rate": 8.30995323981296e-06,
|
| 115 |
+
"loss": 0.0587,
|
| 116 |
+
"step": 7000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.25250501002004,
|
| 120 |
+
"grad_norm": 0.04314618557691574,
|
| 121 |
+
"learning_rate": 7.474949899799599e-06,
|
| 122 |
+
"loss": 0.052,
|
| 123 |
+
"step": 7500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.3360053440213762,
|
| 127 |
+
"grad_norm": 0.008493722416460514,
|
| 128 |
+
"learning_rate": 6.63994655978624e-06,
|
| 129 |
+
"loss": 0.0481,
|
| 130 |
+
"step": 8000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.4195056780227122,
|
| 134 |
+
"grad_norm": 0.08650221675634384,
|
| 135 |
+
"learning_rate": 5.80494321977288e-06,
|
| 136 |
+
"loss": 0.0505,
|
| 137 |
+
"step": 8500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.503006012024048,
|
| 141 |
+
"grad_norm": 0.061995044350624084,
|
| 142 |
+
"learning_rate": 4.969939879759519e-06,
|
| 143 |
+
"loss": 0.0591,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.586506346025384,
|
| 148 |
+
"grad_norm": 0.5668061375617981,
|
| 149 |
+
"learning_rate": 4.1349365397461595e-06,
|
| 150 |
+
"loss": 0.0449,
|
| 151 |
+
"step": 9500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.6700066800267201,
|
| 155 |
+
"grad_norm": 24.995769500732422,
|
| 156 |
+
"learning_rate": 3.2999331997327993e-06,
|
| 157 |
+
"loss": 0.0468,
|
| 158 |
+
"step": 10000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.753507014028056,
|
| 162 |
+
"grad_norm": 0.08540898561477661,
|
| 163 |
+
"learning_rate": 2.464929859719439e-06,
|
| 164 |
+
"loss": 0.0508,
|
| 165 |
+
"step": 10500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.8370073480293923,
|
| 169 |
+
"grad_norm": 0.008522373624145985,
|
| 170 |
+
"learning_rate": 1.629926519706079e-06,
|
| 171 |
+
"loss": 0.0508,
|
| 172 |
+
"step": 11000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.920507682030728,
|
| 176 |
+
"grad_norm": 0.0260649211704731,
|
| 177 |
+
"learning_rate": 7.949231796927188e-07,
|
| 178 |
+
"loss": 0.0369,
|
| 179 |
+
"step": 11500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.0,
|
| 183 |
+
"eval_f1": 0.939003006012024,
|
| 184 |
+
"eval_loss": 0.3057553768157959,
|
| 185 |
+
"eval_runtime": 270.9202,
|
| 186 |
+
"eval_samples_per_second": 88.41,
|
| 187 |
+
"eval_steps_per_second": 5.526,
|
| 188 |
+
"step": 11976
|
| 189 |
+
}
|
| 190 |
+
],
|
| 191 |
+
"logging_steps": 500,
|
| 192 |
+
"max_steps": 11976,
|
| 193 |
+
"num_input_tokens_seen": 0,
|
| 194 |
+
"num_train_epochs": 2,
|
| 195 |
+
"save_steps": 500,
|
| 196 |
+
"stateful_callbacks": {
|
| 197 |
+
"TrainerControl": {
|
| 198 |
+
"args": {
|
| 199 |
+
"should_epoch_stop": false,
|
| 200 |
+
"should_evaluate": false,
|
| 201 |
+
"should_log": false,
|
| 202 |
+
"should_save": true,
|
| 203 |
+
"should_training_stop": true
|
| 204 |
+
},
|
| 205 |
+
"attributes": {}
|
| 206 |
+
}
|
| 207 |
+
},
|
| 208 |
+
"total_flos": 1.261573837252608e+16,
|
| 209 |
+
"train_batch_size": 16,
|
| 210 |
+
"trial_name": null,
|
| 211 |
+
"trial_params": null
|
| 212 |
+
}
|
checkpoint-11976/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:789de4a2b6c30e6874a2920b354aec1ad5e4e55abf36678e20075927918410a2
|
| 3 |
+
size 5368
|
checkpoint-5988/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-5988/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-xsmall",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 384,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "human",
|
| 12 |
+
"1": "machine"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 1536,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"human": 0,
|
| 18 |
+
"machine": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-07,
|
| 21 |
+
"legacy": true,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"max_relative_positions": -1,
|
| 24 |
+
"model_type": "deberta-v2",
|
| 25 |
+
"norm_rel_ebd": "layer_norm",
|
| 26 |
+
"num_attention_heads": 6,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_dropout": 0,
|
| 30 |
+
"pooler_hidden_act": "gelu",
|
| 31 |
+
"pooler_hidden_size": 384,
|
| 32 |
+
"pos_att_type": [
|
| 33 |
+
"p2c",
|
| 34 |
+
"c2p"
|
| 35 |
+
],
|
| 36 |
+
"position_biased_input": false,
|
| 37 |
+
"position_buckets": 256,
|
| 38 |
+
"relative_attention": true,
|
| 39 |
+
"share_att_key": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.47.0",
|
| 42 |
+
"type_vocab_size": 0,
|
| 43 |
+
"vocab_size": 128100
|
| 44 |
+
}
|
checkpoint-5988/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c1b6f5ea2d039b9c9110ade1870be063c10a70afd28849aeaae6c02305d2e0
|
| 3 |
+
size 283347432
|
checkpoint-5988/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2448759def6302a46db7df39300234434637b0185b22395cf24d62f04fc2abbc
|
| 3 |
+
size 566814714
|
checkpoint-5988/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43417117d08f6f1db417ffa5433d4d3c3fa7901dd081de7a8875670a9ec506ad
|
| 3 |
+
size 14244
|
checkpoint-5988/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aec6adcfc715a01b4971f7bd4468cc3d670b55611d5a481b47e778747a988a43
|
| 3 |
+
size 1064
|
checkpoint-5988/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-5988/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-5988/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-5988/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": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
checkpoint-5988/trainer_state.json
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2785227596759796,
|
| 3 |
+
"best_model_checkpoint": "Machine-Generated-Text-Detection/deberta/checkpoint-5988",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5988,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08350033400133601,
|
| 13 |
+
"grad_norm": 1.8728934526443481,
|
| 14 |
+
"learning_rate": 1.9164996659986642e-05,
|
| 15 |
+
"loss": 0.2671,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16700066800267202,
|
| 20 |
+
"grad_norm": 0.5576282143592834,
|
| 21 |
+
"learning_rate": 1.832999331997328e-05,
|
| 22 |
+
"loss": 0.1527,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.250501002004008,
|
| 27 |
+
"grad_norm": 7.88850736618042,
|
| 28 |
+
"learning_rate": 1.7494989979959922e-05,
|
| 29 |
+
"loss": 0.135,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33400133600534404,
|
| 34 |
+
"grad_norm": 0.6910138130187988,
|
| 35 |
+
"learning_rate": 1.6659986639946563e-05,
|
| 36 |
+
"loss": 0.1107,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.41750167000668004,
|
| 41 |
+
"grad_norm": 8.903568267822266,
|
| 42 |
+
"learning_rate": 1.58249832999332e-05,
|
| 43 |
+
"loss": 0.1152,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.501002004008016,
|
| 48 |
+
"grad_norm": 0.08548898249864578,
|
| 49 |
+
"learning_rate": 1.498997995991984e-05,
|
| 50 |
+
"loss": 0.1024,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.584502338009352,
|
| 55 |
+
"grad_norm": 8.673635482788086,
|
| 56 |
+
"learning_rate": 1.415497661990648e-05,
|
| 57 |
+
"loss": 0.0967,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6680026720106881,
|
| 62 |
+
"grad_norm": 7.020376682281494,
|
| 63 |
+
"learning_rate": 1.331997327989312e-05,
|
| 64 |
+
"loss": 0.1024,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.751503006012024,
|
| 69 |
+
"grad_norm": 11.58995532989502,
|
| 70 |
+
"learning_rate": 1.248496993987976e-05,
|
| 71 |
+
"loss": 0.0809,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8350033400133601,
|
| 76 |
+
"grad_norm": 8.78143310546875,
|
| 77 |
+
"learning_rate": 1.16499665998664e-05,
|
| 78 |
+
"loss": 0.0823,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.918503674014696,
|
| 83 |
+
"grad_norm": 9.562505722045898,
|
| 84 |
+
"learning_rate": 1.081496325985304e-05,
|
| 85 |
+
"loss": 0.0769,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_f1": 0.9371242484969939,
|
| 91 |
+
"eval_loss": 0.2785227596759796,
|
| 92 |
+
"eval_runtime": 269.2073,
|
| 93 |
+
"eval_samples_per_second": 88.972,
|
| 94 |
+
"eval_steps_per_second": 5.561,
|
| 95 |
+
"step": 5988
|
| 96 |
+
}
|
| 97 |
+
],
|
| 98 |
+
"logging_steps": 500,
|
| 99 |
+
"max_steps": 11976,
|
| 100 |
+
"num_input_tokens_seen": 0,
|
| 101 |
+
"num_train_epochs": 2,
|
| 102 |
+
"save_steps": 500,
|
| 103 |
+
"stateful_callbacks": {
|
| 104 |
+
"TrainerControl": {
|
| 105 |
+
"args": {
|
| 106 |
+
"should_epoch_stop": false,
|
| 107 |
+
"should_evaluate": false,
|
| 108 |
+
"should_log": false,
|
| 109 |
+
"should_save": true,
|
| 110 |
+
"should_training_stop": false
|
| 111 |
+
},
|
| 112 |
+
"attributes": {}
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
"total_flos": 6307877420649216.0,
|
| 116 |
+
"train_batch_size": 16,
|
| 117 |
+
"trial_name": null,
|
| 118 |
+
"trial_params": null
|
| 119 |
+
}
|
checkpoint-5988/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:789de4a2b6c30e6874a2920b354aec1ad5e4e55abf36678e20075927918410a2
|
| 3 |
+
size 5368
|