uvegesistvan commited on
Commit
85b6f63
·
verified ·
1 Parent(s): 5cab4c6

Upload folder using huggingface_hub

Browse files
checkpoint-15528/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "problem_type": "single_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.48.0",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
checkpoint-15528/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1c01a7932118cbe07690383d4886f399cb977acddf0aff4a43a0d994b86e5d
3
+ size 2239647372
checkpoint-15528/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32c5199fbd449e6d27595aaba5fe239943f38a1c46ceda540eae591d5333652
3
+ size 4479530129
checkpoint-15528/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56e9c28cdb26ff4b365053edc1077189a0a5a27578b62f3e57bc84f4c2581bf
3
+ size 14244
checkpoint-15528/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86818efe582b607a9fe153390ecab002b3b24eeecb82ead566bbb871d1abb72d
3
+ size 1064
checkpoint-15528/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8398369550704956,
3
+ "best_model_checkpoint": "model/checkpoint-15528",
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 15528,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 4.337671756744385,
14
+ "learning_rate": 8.333333333333334e-06,
15
+ "loss": 1.1662,
16
+ "step": 3882
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6617722823286966,
21
+ "eval_f1": 0.6680424548058616,
22
+ "eval_loss": 0.9114612340927124,
23
+ "eval_precision": 0.7123936564476506,
24
+ "eval_recall": 0.6617722823286966,
25
+ "eval_runtime": 100.3662,
26
+ "eval_samples_per_second": 77.357,
27
+ "eval_steps_per_second": 4.842,
28
+ "step": 3882
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 27.886930465698242,
33
+ "learning_rate": 6.666666666666667e-06,
34
+ "loss": 0.8362,
35
+ "step": 7764
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7022153529108707,
40
+ "eval_f1": 0.703267188858009,
41
+ "eval_loss": 0.8457719683647156,
42
+ "eval_precision": 0.706096751630033,
43
+ "eval_recall": 0.7022153529108707,
44
+ "eval_runtime": 101.2974,
45
+ "eval_samples_per_second": 76.646,
46
+ "eval_steps_per_second": 4.798,
47
+ "step": 7764
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 26.243642807006836,
52
+ "learning_rate": 5e-06,
53
+ "loss": 0.7417,
54
+ "step": 11646
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7076249356002061,
59
+ "eval_f1": 0.7076968431936885,
60
+ "eval_loss": 0.8539687395095825,
61
+ "eval_precision": 0.7106108131996597,
62
+ "eval_recall": 0.7076249356002061,
63
+ "eval_runtime": 101.1551,
64
+ "eval_samples_per_second": 76.753,
65
+ "eval_steps_per_second": 4.805,
66
+ "step": 11646
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 31.632232666015625,
71
+ "learning_rate": 3.3333333333333333e-06,
72
+ "loss": 0.6682,
73
+ "step": 15528
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.7162545079855744,
78
+ "eval_f1": 0.7179259204981147,
79
+ "eval_loss": 0.8398369550704956,
80
+ "eval_precision": 0.7209674732818927,
81
+ "eval_recall": 0.7162545079855744,
82
+ "eval_runtime": 100.8845,
83
+ "eval_samples_per_second": 76.959,
84
+ "eval_steps_per_second": 4.817,
85
+ "step": 15528
86
+ }
87
+ ],
88
+ "logging_steps": 100,
89
+ "max_steps": 23292,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 6,
92
+ "save_steps": 100,
93
+ "stateful_callbacks": {
94
+ "EarlyStoppingCallback": {
95
+ "args": {
96
+ "early_stopping_patience": 2,
97
+ "early_stopping_threshold": 0.0
98
+ },
99
+ "attributes": {
100
+ "early_stopping_patience_counter": 0
101
+ }
102
+ },
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": false
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 1.1575420461248717e+17,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-15528/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
3
+ size 5240
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "xlm-roberta",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "problem_type": "single_label_classification",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.48.0",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
+ }
events.out.tfevents.1734268801.5dc78d0c0094.597.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc1315c7e1f2183cb5b32925df2e7b72f36542226b646d07a45f3c2ae0533f0
3
+ size 8513
events.out.tfevents.1734292683.26dae68edbc1.519.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153851a01c1db2c0602694cc5524d930f1f95c7a7c3a8cd4d23bbb7b09b9dc0a
3
+ size 5395
events.out.tfevents.1734293482.15565a6fdb0d.517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5315719c053e1861da202c80e15d78116f848d40ccf4a2f40dcb34688c8375dc
3
+ size 7444
events.out.tfevents.1734299316.15565a6fdb0d.14799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30436099c0ccf2daef57aa51b47cca5db54f956c27940eddb55b1a3664918dc
3
+ size 8481
events.out.tfevents.1734305996.15565a6fdb0d.14799.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60026a51a67f1cd87355d4a35d74e7f092d77e110549e5808328478f692f45f4
3
+ size 9164
events.out.tfevents.1736275701.ccf8e4cfc100.602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f36308fbef6bcf0fd81c4e7d64d450c8eaf5800a624df96fa1aa07a6895801
3
+ size 5395
events.out.tfevents.1736278450.ccf8e4cfc100.602.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f65837e8097fba7e1c62f4323abc004c45d8d76c915594caedfac13d1992850
3
+ size 9183
events.out.tfevents.1736347759.affcea672b22.1013.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eddd5f5bb8672975a8cd0b0171c1ba334ad85b542ee025aa522b9df4570fa05
3
+ size 5395
events.out.tfevents.1736347909.a7ec1308ad87.517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bcc672afaf6045e973673ac75f3625ea2ad3cacf8d098f50e4385bad595f79
3
+ size 5395
events.out.tfevents.1736348086.a7ec1308ad87.1015.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf5216291240dba6beaa7e66bdb7888f5b358c46ed8ddd08f935a4e380772ec
3
+ size 5395
events.out.tfevents.1736348328.892f0a65915d.511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222f7266238deb428ba3800c68968ba8f80f58aa05b3318929ffb0a9a7e5b1e9
3
+ size 8481
events.out.tfevents.1736529172.1a9a4426b2c0.783.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33eb538b3bfb14a8557b8f6934c99a2e7e2dd0f44dc3356c508585c116b54c6a
3
+ size 5395
events.out.tfevents.1736529480.a0c18d20ace0.511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b325f8dcf516b2f62ef7c4afcd44f3ee3e91cf458292cf54c978f60e03335e
3
+ size 8481
events.out.tfevents.1736549406.f0c728e9d75e.800.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad8887dbed3fc02d3433ce314d61e48216fcfe486bfb03b775b46e8b096da25
3
+ size 9879
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1c01a7932118cbe07690383d4886f399cb977acddf0aff4a43a0d994b86e5d
3
+ size 2239647372
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
3
+ size 5240