Hugging Face's logo

backzone1
/
FI-Chat-Classify

Text Classification
PyTorch
Thai
deberta-v2
thai
fine-tuned
custom-model
Model card Files
xet
Community
6
backzone1 commited on
Commit
91a52c5
·
verified ·
1 Parent(s): dd20d07

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +2 -0
  2. checkpoint-176/config.json +43 -0
  3. checkpoint-176/special_tokens_map.json +51 -0
  4. checkpoint-176/tokenizer.json +3 -0
  5. checkpoint-176/tokenizer_config.json +59 -0
  6. checkpoint-176/trainer_state.json +153 -0
  7. checkpoint-176/training_args.bin +3 -0
  8. checkpoint-220/config.json +43 -0
  9. checkpoint-220/special_tokens_map.json +51 -0
  10. checkpoint-220/tokenizer.json +3 -0
  11. checkpoint-220/tokenizer_config.json +59 -0
  12. checkpoint-220/trainer_state.json +188 -0
  13. checkpoint-220/training_args.bin +3 -0
  14. pytorch_model.bin +1 -1
.gitattributes CHANGED
@@ -43,3 +43,5 @@ checkpoint-612/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  checkpoint-765/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
  checkpoint-95/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
43
  checkpoint-765/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
  checkpoint-95/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-176/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-176/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "\u0e01\u0e32\u0e23\u0e08\u0e49\u0e32\u0e07\u0e23\u0e16\u0e23\u0e31\u0e1a\u0e2a\u0e48\u0e07\u0e2a\u0e34\u0e19\u0e04\u0e49\u0e32",
11
+ "1": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e01\u0e32\u0e23\u0e08\u0e49\u0e32\u0e07\u0e23\u0e16\u0e23\u0e31\u0e1a\u0e2a\u0e48\u0e07\u0e2a\u0e34\u0e19\u0e04\u0e49\u0e32"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "label2id": {
16
+ "entailment": 0,
17
+ "not_entailment": 1
18
+ },
19
+ "layer_norm_eps": 1e-07,
20
+ "legacy": true,
21
+ "max_position_embeddings": 512,
22
+ "max_relative_positions": -1,
23
+ "model_type": "deberta-v2",
24
+ "norm_rel_ebd": "layer_norm",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "pooler_dropout": 0,
29
+ "pooler_hidden_act": "gelu",
30
+ "pooler_hidden_size": 768,
31
+ "pos_att_type": [
32
+ "p2c",
33
+ "c2p"
34
+ ],
35
+ "position_biased_input": false,
36
+ "position_buckets": 256,
37
+ "relative_attention": true,
38
+ "share_att_key": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.52.4",
41
+ "type_vocab_size": 0,
42
+ "vocab_size": 251000
43
+ }
checkpoint-176/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-176/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
3
+ size 16316224
checkpoint-176/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
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
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-176/trainer_state.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 176,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.22727272727272727,
14
+ "grad_norm": 8.667610168457031,
15
+ "learning_rate": 1.9181818181818183e-05,
16
+ "loss": 0.5911,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.45454545454545453,
21
+ "grad_norm": 6.615207672119141,
22
+ "learning_rate": 1.8272727272727275e-05,
23
+ "loss": 0.464,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.6818181818181818,
28
+ "grad_norm": 13.182315826416016,
29
+ "learning_rate": 1.7363636363636363e-05,
30
+ "loss": 0.3223,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9090909090909091,
35
+ "grad_norm": 8.283531188964844,
36
+ "learning_rate": 1.6454545454545455e-05,
37
+ "loss": 0.2932,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.1363636363636362,
42
+ "grad_norm": 2.350064277648926,
43
+ "learning_rate": 1.5545454545454547e-05,
44
+ "loss": 0.3104,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.3636363636363638,
49
+ "grad_norm": 1.3099472522735596,
50
+ "learning_rate": 1.4636363636363637e-05,
51
+ "loss": 0.2794,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.5909090909090908,
56
+ "grad_norm": 0.701838493347168,
57
+ "learning_rate": 1.3727272727272729e-05,
58
+ "loss": 0.1536,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.8181818181818183,
63
+ "grad_norm": 0.7129743695259094,
64
+ "learning_rate": 1.281818181818182e-05,
65
+ "loss": 0.2083,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 2.0454545454545454,
70
+ "grad_norm": 5.099246025085449,
71
+ "learning_rate": 1.190909090909091e-05,
72
+ "loss": 0.1498,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 2.2727272727272725,
77
+ "grad_norm": 25.056194305419922,
78
+ "learning_rate": 1.1000000000000001e-05,
79
+ "loss": 0.2337,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 2.5,
84
+ "grad_norm": 27.893611907958984,
85
+ "learning_rate": 1.0090909090909092e-05,
86
+ "loss": 0.1566,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.7272727272727275,
91
+ "grad_norm": 0.9230498671531677,
92
+ "learning_rate": 9.181818181818184e-06,
93
+ "loss": 0.1208,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 2.9545454545454546,
98
+ "grad_norm": 0.20559445023536682,
99
+ "learning_rate": 8.272727272727274e-06,
100
+ "loss": 0.2526,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 3.1818181818181817,
105
+ "grad_norm": 8.288787841796875,
106
+ "learning_rate": 7.363636363636364e-06,
107
+ "loss": 0.1241,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 3.409090909090909,
112
+ "grad_norm": 0.2578887343406677,
113
+ "learning_rate": 6.454545454545456e-06,
114
+ "loss": 0.1863,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 3.6363636363636362,
119
+ "grad_norm": 0.26157981157302856,
120
+ "learning_rate": 5.545454545454546e-06,
121
+ "loss": 0.1131,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 3.8636363636363638,
126
+ "grad_norm": 10.041345596313477,
127
+ "learning_rate": 4.636363636363636e-06,
128
+ "loss": 0.1458,
129
+ "step": 170
130
+ }
131
+ ],
132
+ "logging_steps": 10,
133
+ "max_steps": 220,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 5,
136
+ "save_steps": 500,
137
+ "stateful_callbacks": {
138
+ "TrainerControl": {
139
+ "args": {
140
+ "should_epoch_stop": false,
141
+ "should_evaluate": false,
142
+ "should_log": false,
143
+ "should_save": true,
144
+ "should_training_stop": false
145
+ },
146
+ "attributes": {}
147
+ }
148
+ },
149
+ "total_flos": 99723447817788.0,
150
+ "train_batch_size": 8,
151
+ "trial_name": null,
152
+ "trial_params": null
153
+ }
checkpoint-176/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8f550d6d3617db1b6992d1d5c428d1c2201c6e42324b75997f5dd20f4df04e
3
+ size 5649
checkpoint-220/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "\u0e01\u0e32\u0e23\u0e08\u0e49\u0e32\u0e07\u0e23\u0e16\u0e23\u0e31\u0e1a\u0e2a\u0e48\u0e07\u0e2a\u0e34\u0e19\u0e04\u0e49\u0e32",
11
+ "1": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e01\u0e32\u0e23\u0e08\u0e49\u0e32\u0e07\u0e23\u0e16\u0e23\u0e31\u0e1a\u0e2a\u0e48\u0e07\u0e2a\u0e34\u0e19\u0e04\u0e49\u0e32"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "label2id": {
16
+ "entailment": 0,
17
+ "not_entailment": 1
18
+ },
19
+ "layer_norm_eps": 1e-07,
20
+ "legacy": true,
21
+ "max_position_embeddings": 512,
22
+ "max_relative_positions": -1,
23
+ "model_type": "deberta-v2",
24
+ "norm_rel_ebd": "layer_norm",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "pooler_dropout": 0,
29
+ "pooler_hidden_act": "gelu",
30
+ "pooler_hidden_size": 768,
31
+ "pos_att_type": [
32
+ "p2c",
33
+ "c2p"
34
+ ],
35
+ "position_biased_input": false,
36
+ "position_buckets": 256,
37
+ "relative_attention": true,
38
+ "share_att_key": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.52.4",
41
+ "type_vocab_size": 0,
42
+ "vocab_size": 251000
43
+ }
checkpoint-220/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-220/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
3
+ size 16316224
checkpoint-220/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
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
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-220/trainer_state.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 220,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.22727272727272727,
14
+ "grad_norm": 8.667610168457031,
15
+ "learning_rate": 1.9181818181818183e-05,
16
+ "loss": 0.5911,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.45454545454545453,
21
+ "grad_norm": 6.615207672119141,
22
+ "learning_rate": 1.8272727272727275e-05,
23
+ "loss": 0.464,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.6818181818181818,
28
+ "grad_norm": 13.182315826416016,
29
+ "learning_rate": 1.7363636363636363e-05,
30
+ "loss": 0.3223,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.9090909090909091,
35
+ "grad_norm": 8.283531188964844,
36
+ "learning_rate": 1.6454545454545455e-05,
37
+ "loss": 0.2932,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.1363636363636362,
42
+ "grad_norm": 2.350064277648926,
43
+ "learning_rate": 1.5545454545454547e-05,
44
+ "loss": 0.3104,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.3636363636363638,
49
+ "grad_norm": 1.3099472522735596,
50
+ "learning_rate": 1.4636363636363637e-05,
51
+ "loss": 0.2794,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.5909090909090908,
56
+ "grad_norm": 0.701838493347168,
57
+ "learning_rate": 1.3727272727272729e-05,
58
+ "loss": 0.1536,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.8181818181818183,
63
+ "grad_norm": 0.7129743695259094,
64
+ "learning_rate": 1.281818181818182e-05,
65
+ "loss": 0.2083,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 2.0454545454545454,
70
+ "grad_norm": 5.099246025085449,
71
+ "learning_rate": 1.190909090909091e-05,
72
+ "loss": 0.1498,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 2.2727272727272725,
77
+ "grad_norm": 25.056194305419922,
78
+ "learning_rate": 1.1000000000000001e-05,
79
+ "loss": 0.2337,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 2.5,
84
+ "grad_norm": 27.893611907958984,
85
+ "learning_rate": 1.0090909090909092e-05,
86
+ "loss": 0.1566,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.7272727272727275,
91
+ "grad_norm": 0.9230498671531677,
92
+ "learning_rate": 9.181818181818184e-06,
93
+ "loss": 0.1208,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 2.9545454545454546,
98
+ "grad_norm": 0.20559445023536682,
99
+ "learning_rate": 8.272727272727274e-06,
100
+ "loss": 0.2526,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 3.1818181818181817,
105
+ "grad_norm": 8.288787841796875,
106
+ "learning_rate": 7.363636363636364e-06,
107
+ "loss": 0.1241,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 3.409090909090909,
112
+ "grad_norm": 0.2578887343406677,
113
+ "learning_rate": 6.454545454545456e-06,
114
+ "loss": 0.1863,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 3.6363636363636362,
119
+ "grad_norm": 0.26157981157302856,
120
+ "learning_rate": 5.545454545454546e-06,
121
+ "loss": 0.1131,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 3.8636363636363638,
126
+ "grad_norm": 10.041345596313477,
127
+ "learning_rate": 4.636363636363636e-06,
128
+ "loss": 0.1458,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 4.090909090909091,
133
+ "grad_norm": 0.2509705126285553,
134
+ "learning_rate": 3.727272727272728e-06,
135
+ "loss": 0.0781,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 4.318181818181818,
140
+ "grad_norm": 0.141200453042984,
141
+ "learning_rate": 2.818181818181818e-06,
142
+ "loss": 0.1208,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 4.545454545454545,
147
+ "grad_norm": 0.3103751242160797,
148
+ "learning_rate": 1.9090909090909095e-06,
149
+ "loss": 0.0898,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 4.7727272727272725,
154
+ "grad_norm": 0.1590297371149063,
155
+ "learning_rate": 1.0000000000000002e-06,
156
+ "loss": 0.1013,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 5.0,
161
+ "grad_norm": 67.25486755371094,
162
+ "learning_rate": 9.090909090909091e-08,
163
+ "loss": 0.2334,
164
+ "step": 220
165
+ }
166
+ ],
167
+ "logging_steps": 10,
168
+ "max_steps": 220,
169
+ "num_input_tokens_seen": 0,
170
+ "num_train_epochs": 5,
171
+ "save_steps": 500,
172
+ "stateful_callbacks": {
173
+ "TrainerControl": {
174
+ "args": {
175
+ "should_epoch_stop": false,
176
+ "should_evaluate": false,
177
+ "should_log": false,
178
+ "should_save": true,
179
+ "should_training_stop": true
180
+ },
181
+ "attributes": {}
182
+ }
183
+ },
184
+ "total_flos": 124877726925996.0,
185
+ "train_batch_size": 8,
186
+ "trial_name": null,
187
+ "trial_params": null
188
+ }
checkpoint-220/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8f550d6d3617db1b6992d1d5c428d1c2201c6e42324b75997f5dd20f4df04e
3
+ size 5649
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb3d53157b1bfdf6a32cdfdf790ed619948436ab4fab0ef97fa026489262246
3
  size 1115313995
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d47d0cdfb0bc4adbe4210fff08aef1bb071a5283d89101140a598926f7acfda
3
  size 1115313995