azande7 commited on
Commit
8f6ece7
·
verified ·
1 Parent(s): 5186a8e

Upload 22 files

Browse files
results/checkpoint-1841/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Negative",
13
+ "1": "Neutral",
14
+ "2": "Positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Negative": 0,
19
+ "Neutral": 1,
20
+ "Positive": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "transformers_version": "4.57.1",
33
+ "vocab_size": 30522
34
+ }
results/checkpoint-1841/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66498eb0c0e918041af10215a6753716764e73e4defff20b95cbccd5497d0d2
3
+ size 267835644
results/checkpoint-1841/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295058f788e222dd1d9dd0f0c9794aed8eaabc8dd6444a14bda3fbf2e156c07e
3
+ size 535731019
results/checkpoint-1841/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
3
+ size 14455
results/checkpoint-1841/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec48a14e1a1b535ec402be1904f700a77d759f9166c15d8a11b4712f4699924
3
+ size 1465
results/checkpoint-1841/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
+ }
results/checkpoint-1841/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
results/checkpoint-1841/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
results/checkpoint-1841/trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1841,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.054318305268875614,
14
+ "grad_norm": 7.17081356048584,
15
+ "learning_rate": 1.9462248777838134e-05,
16
+ "loss": 0.829,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.10863661053775123,
21
+ "grad_norm": 3.1564130783081055,
22
+ "learning_rate": 1.8919065725149376e-05,
23
+ "loss": 0.5487,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.16295491580662683,
28
+ "grad_norm": 8.601940155029297,
29
+ "learning_rate": 1.837588267246062e-05,
30
+ "loss": 0.5025,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.21727322107550245,
35
+ "grad_norm": 15.523472785949707,
36
+ "learning_rate": 1.7832699619771866e-05,
37
+ "loss": 0.4689,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.27159152634437805,
42
+ "grad_norm": 15.09040355682373,
43
+ "learning_rate": 1.7289516567083108e-05,
44
+ "loss": 0.4834,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.32590983161325365,
49
+ "grad_norm": 19.788265228271484,
50
+ "learning_rate": 1.6746333514394353e-05,
51
+ "loss": 0.5369,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.38022813688212925,
56
+ "grad_norm": 3.3475818634033203,
57
+ "learning_rate": 1.6203150461705595e-05,
58
+ "loss": 0.4664,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.4345464421510049,
63
+ "grad_norm": 14.11961841583252,
64
+ "learning_rate": 1.565996740901684e-05,
65
+ "loss": 0.4521,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.4888647474198805,
70
+ "grad_norm": 19.61833953857422,
71
+ "learning_rate": 1.5116784356328084e-05,
72
+ "loss": 0.4495,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.5431830526887561,
77
+ "grad_norm": 4.591318130493164,
78
+ "learning_rate": 1.457360130363933e-05,
79
+ "loss": 0.4485,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.5975013579576317,
84
+ "grad_norm": 2.7707386016845703,
85
+ "learning_rate": 1.4030418250950571e-05,
86
+ "loss": 0.4497,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.6518196632265073,
91
+ "grad_norm": 17.942611694335938,
92
+ "learning_rate": 1.3487235198261815e-05,
93
+ "loss": 0.4026,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.7061379684953829,
98
+ "grad_norm": 13.72081184387207,
99
+ "learning_rate": 1.2944052145573058e-05,
100
+ "loss": 0.4697,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.7604562737642585,
105
+ "grad_norm": 23.541465759277344,
106
+ "learning_rate": 1.2400869092884302e-05,
107
+ "loss": 0.3684,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.8147745790331342,
112
+ "grad_norm": 4.5846943855285645,
113
+ "learning_rate": 1.1857686040195547e-05,
114
+ "loss": 0.4219,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.8690928843020098,
119
+ "grad_norm": 21.806142807006836,
120
+ "learning_rate": 1.131450298750679e-05,
121
+ "loss": 0.4278,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.9234111895708854,
126
+ "grad_norm": 6.823528289794922,
127
+ "learning_rate": 1.0771319934818034e-05,
128
+ "loss": 0.4095,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.977729494839761,
133
+ "grad_norm": 19.248985290527344,
134
+ "learning_rate": 1.0228136882129278e-05,
135
+ "loss": 0.3996,
136
+ "step": 1800
137
+ }
138
+ ],
139
+ "logging_steps": 100,
140
+ "max_steps": 3682,
141
+ "num_input_tokens_seen": 0,
142
+ "num_train_epochs": 2,
143
+ "save_steps": 500,
144
+ "stateful_callbacks": {
145
+ "TrainerControl": {
146
+ "args": {
147
+ "should_epoch_stop": false,
148
+ "should_evaluate": false,
149
+ "should_log": false,
150
+ "should_save": true,
151
+ "should_training_stop": false
152
+ },
153
+ "attributes": {}
154
+ }
155
+ },
156
+ "total_flos": 487687425209856.0,
157
+ "train_batch_size": 8,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
results/checkpoint-1841/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde76f0a5d8c6c568434f9dc3633934a48220d6abfa75a8ac99eb66c5eaf8380
3
+ size 5777
results/checkpoint-1841/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
results/checkpoint-3682/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Negative",
13
+ "1": "Neutral",
14
+ "2": "Positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "Negative": 0,
19
+ "Neutral": 1,
20
+ "Positive": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "transformers_version": "4.57.1",
33
+ "vocab_size": 30522
34
+ }
results/checkpoint-3682/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ac71e5e8ca19c3a32df5f76443b8ae228f949c4026d1e9b03d8cd2eb2385e1
3
+ size 267835644
results/checkpoint-3682/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb22764a1d45ca282507a4c36b0a57db8a685473a19c91febb9a39abe80091f
3
+ size 535731019
results/checkpoint-3682/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a77d4a8b98ce027a4d6a3b9fb5d7c904e27ec1efd5c0468c24fa26bb738316
3
+ size 14455
results/checkpoint-3682/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f58823bfa352b1e9ab22ebd1b8259c15017295a02ec78cebbbdd922227ac3fa
3
+ size 1465
results/checkpoint-3682/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
+ }
results/checkpoint-3682/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
results/checkpoint-3682/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
results/checkpoint-3682/trainer_state.json ADDED
@@ -0,0 +1,286 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3682,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.054318305268875614,
14
+ "grad_norm": 7.17081356048584,
15
+ "learning_rate": 1.9462248777838134e-05,
16
+ "loss": 0.829,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.10863661053775123,
21
+ "grad_norm": 3.1564130783081055,
22
+ "learning_rate": 1.8919065725149376e-05,
23
+ "loss": 0.5487,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.16295491580662683,
28
+ "grad_norm": 8.601940155029297,
29
+ "learning_rate": 1.837588267246062e-05,
30
+ "loss": 0.5025,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.21727322107550245,
35
+ "grad_norm": 15.523472785949707,
36
+ "learning_rate": 1.7832699619771866e-05,
37
+ "loss": 0.4689,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.27159152634437805,
42
+ "grad_norm": 15.09040355682373,
43
+ "learning_rate": 1.7289516567083108e-05,
44
+ "loss": 0.4834,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.32590983161325365,
49
+ "grad_norm": 19.788265228271484,
50
+ "learning_rate": 1.6746333514394353e-05,
51
+ "loss": 0.5369,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.38022813688212925,
56
+ "grad_norm": 3.3475818634033203,
57
+ "learning_rate": 1.6203150461705595e-05,
58
+ "loss": 0.4664,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.4345464421510049,
63
+ "grad_norm": 14.11961841583252,
64
+ "learning_rate": 1.565996740901684e-05,
65
+ "loss": 0.4521,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.4888647474198805,
70
+ "grad_norm": 19.61833953857422,
71
+ "learning_rate": 1.5116784356328084e-05,
72
+ "loss": 0.4495,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.5431830526887561,
77
+ "grad_norm": 4.591318130493164,
78
+ "learning_rate": 1.457360130363933e-05,
79
+ "loss": 0.4485,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.5975013579576317,
84
+ "grad_norm": 2.7707386016845703,
85
+ "learning_rate": 1.4030418250950571e-05,
86
+ "loss": 0.4497,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.6518196632265073,
91
+ "grad_norm": 17.942611694335938,
92
+ "learning_rate": 1.3487235198261815e-05,
93
+ "loss": 0.4026,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.7061379684953829,
98
+ "grad_norm": 13.72081184387207,
99
+ "learning_rate": 1.2944052145573058e-05,
100
+ "loss": 0.4697,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.7604562737642585,
105
+ "grad_norm": 23.541465759277344,
106
+ "learning_rate": 1.2400869092884302e-05,
107
+ "loss": 0.3684,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.8147745790331342,
112
+ "grad_norm": 4.5846943855285645,
113
+ "learning_rate": 1.1857686040195547e-05,
114
+ "loss": 0.4219,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.8690928843020098,
119
+ "grad_norm": 21.806142807006836,
120
+ "learning_rate": 1.131450298750679e-05,
121
+ "loss": 0.4278,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.9234111895708854,
126
+ "grad_norm": 6.823528289794922,
127
+ "learning_rate": 1.0771319934818034e-05,
128
+ "loss": 0.4095,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.977729494839761,
133
+ "grad_norm": 19.248985290527344,
134
+ "learning_rate": 1.0228136882129278e-05,
135
+ "loss": 0.3996,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 1.0320478001086366,
140
+ "grad_norm": 6.681798458099365,
141
+ "learning_rate": 9.684953829440523e-06,
142
+ "loss": 0.3415,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 1.0863661053775122,
147
+ "grad_norm": 6.824921131134033,
148
+ "learning_rate": 9.141770776751766e-06,
149
+ "loss": 0.2791,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 1.1406844106463878,
154
+ "grad_norm": 15.584657669067383,
155
+ "learning_rate": 8.59858772406301e-06,
156
+ "loss": 0.2483,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 1.1950027159152634,
161
+ "grad_norm": 26.86137580871582,
162
+ "learning_rate": 8.055404671374254e-06,
163
+ "loss": 0.2541,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 1.249321021184139,
168
+ "grad_norm": 18.813024520874023,
169
+ "learning_rate": 7.512221618685498e-06,
170
+ "loss": 0.2719,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 1.3036393264530146,
175
+ "grad_norm": 2.380384922027588,
176
+ "learning_rate": 6.9690385659967415e-06,
177
+ "loss": 0.2681,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 1.3579576317218902,
182
+ "grad_norm": 14.81904411315918,
183
+ "learning_rate": 6.425855513307986e-06,
184
+ "loss": 0.3181,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 1.4122759369907658,
189
+ "grad_norm": 10.852340698242188,
190
+ "learning_rate": 5.882672460619229e-06,
191
+ "loss": 0.2803,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 1.4665942422596414,
196
+ "grad_norm": 11.246688842773438,
197
+ "learning_rate": 5.339489407930473e-06,
198
+ "loss": 0.3213,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 1.5209125475285172,
203
+ "grad_norm": 15.644658088684082,
204
+ "learning_rate": 4.7963063552417165e-06,
205
+ "loss": 0.2609,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 1.5752308527973926,
210
+ "grad_norm": 29.03853416442871,
211
+ "learning_rate": 4.253123302552961e-06,
212
+ "loss": 0.265,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 1.6295491580662684,
217
+ "grad_norm": 18.956375122070312,
218
+ "learning_rate": 3.7099402498642045e-06,
219
+ "loss": 0.277,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 1.6838674633351438,
224
+ "grad_norm": 21.82999610900879,
225
+ "learning_rate": 3.1667571971754484e-06,
226
+ "loss": 0.3259,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 1.7381857686040196,
231
+ "grad_norm": 0.2387368232011795,
232
+ "learning_rate": 2.6235741444866924e-06,
233
+ "loss": 0.2902,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 1.792504073872895,
238
+ "grad_norm": 0.8520351052284241,
239
+ "learning_rate": 2.080391091797936e-06,
240
+ "loss": 0.2338,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 1.8468223791417708,
245
+ "grad_norm": 4.296932697296143,
246
+ "learning_rate": 1.53720803910918e-06,
247
+ "loss": 0.2347,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 1.9011406844106464,
252
+ "grad_norm": 18.714519500732422,
253
+ "learning_rate": 9.940249864204237e-07,
254
+ "loss": 0.2805,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 1.955458989679522,
259
+ "grad_norm": 1.6248631477355957,
260
+ "learning_rate": 4.508419337316676e-07,
261
+ "loss": 0.2701,
262
+ "step": 3600
263
+ }
264
+ ],
265
+ "logging_steps": 100,
266
+ "max_steps": 3682,
267
+ "num_input_tokens_seen": 0,
268
+ "num_train_epochs": 2,
269
+ "save_steps": 500,
270
+ "stateful_callbacks": {
271
+ "TrainerControl": {
272
+ "args": {
273
+ "should_epoch_stop": false,
274
+ "should_evaluate": false,
275
+ "should_log": false,
276
+ "should_save": true,
277
+ "should_training_stop": true
278
+ },
279
+ "attributes": {}
280
+ }
281
+ },
282
+ "total_flos": 975374850419712.0,
283
+ "train_batch_size": 8,
284
+ "trial_name": null,
285
+ "trial_params": null
286
+ }
results/checkpoint-3682/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde76f0a5d8c6c568434f9dc3633934a48220d6abfa75a8ac99eb66c5eaf8380
3
+ size 5777
results/checkpoint-3682/vocab.txt ADDED
The diff for this file is too large to render. See raw diff