Bagus commited on
Commit
a0518cd
1 Parent(s): ecbbbd0

Update from bagus

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.99,
3
+ "eval_accuracy": 0.9008264541625977,
4
+ "eval_loss": 0.3769935369491577,
5
+ "eval_runtime": 72.4575,
6
+ "eval_samples": 121,
7
+ "eval_samples_per_second": 1.67,
8
+ "eval_steps_per_second": 0.428,
9
+ "train_loss": 0.7233316548665365,
10
+ "train_runtime": 4793.1545,
11
+ "train_samples": 483,
12
+ "train_samples_per_second": 0.504,
13
+ "train_steps_per_second": 0.063
14
+ }
checkpoint-200/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lighteternal/wav2vec2-large-xlsr-53-greek",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForSpeechClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 256,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": true,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.0,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "finetuning_task": "wav2vec2_clf",
53
+ "gradient_checkpointing": true,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.1,
56
+ "hidden_size": 1024,
57
+ "id2label": {
58
+ "0": "anger",
59
+ "1": "disgust",
60
+ "2": "fear",
61
+ "3": "happiness",
62
+ "4": "sadness"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 4096,
66
+ "label2id": {
67
+ "anger": 0,
68
+ "disgust": 1,
69
+ "fear": 2,
70
+ "happiness": 3,
71
+ "sadness": 4
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.1,
75
+ "mask_channel_length": 10,
76
+ "mask_channel_min_space": 1,
77
+ "mask_channel_other": 0.0,
78
+ "mask_channel_prob": 0.0,
79
+ "mask_channel_selection": "static",
80
+ "mask_feature_length": 10,
81
+ "mask_feature_prob": 0.0,
82
+ "mask_time_length": 10,
83
+ "mask_time_min_space": 1,
84
+ "mask_time_other": 0.0,
85
+ "mask_time_prob": 0.05,
86
+ "mask_time_selection": "static",
87
+ "model_type": "wav2vec2",
88
+ "num_attention_heads": 16,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 24,
95
+ "num_negatives": 100,
96
+ "pad_token_id": 54,
97
+ "pooling_mode": "mean",
98
+ "problem_type": "single_label_classification",
99
+ "proj_codevector_dim": 256,
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.11.0.dev0",
102
+ "use_weighted_layer_sum": false,
103
+ "vocab_size": 55
104
+ }
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3ef445c6fb50c1338404f0f8ef094ced0b8148a9e01ea05ab6e8ed30c6c1cf
3
+ size 2498486409
checkpoint-200/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d48786e73089772715dbc0e246bf38a02c4d938183e949368c55d8e1244058ce
3
+ size 1266137389
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e688113e49819920cd4a81b009685c43d55816d9594ccd778031c8e3ebb6b4d2
3
+ size 13547
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633ffeda9b47d6f109f95c06f42f1a61e840f7a142b896b9ee7ac2b01370b9c7
3
+ size 623
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.330578512396694,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.66,
12
+ "learning_rate": 6.666666666666667e-05,
13
+ "loss": 1.3311,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 1.66,
18
+ "eval_accuracy": 0.6033057570457458,
19
+ "eval_loss": 1.0739655494689941,
20
+ "eval_runtime": 74.6016,
21
+ "eval_samples_per_second": 1.622,
22
+ "eval_steps_per_second": 0.416,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 3.33,
27
+ "learning_rate": 3.3333333333333335e-05,
28
+ "loss": 0.6235,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 3.33,
33
+ "eval_accuracy": 0.8512396812438965,
34
+ "eval_loss": 0.47899967432022095,
35
+ "eval_runtime": 71.6672,
36
+ "eval_samples_per_second": 1.688,
37
+ "eval_steps_per_second": 0.433,
38
+ "step": 200
39
+ }
40
+ ],
41
+ "max_steps": 300,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 2.8587463417327757e+17,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfa74cde1a819557f67b8d79ebbc972342f238ccab6b70489c4baf413332bb7
3
+ size 2799
checkpoint-300/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lighteternal/wav2vec2-large-xlsr-53-greek",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForSpeechClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 256,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": true,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.0,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "finetuning_task": "wav2vec2_clf",
53
+ "gradient_checkpointing": true,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.1,
56
+ "hidden_size": 1024,
57
+ "id2label": {
58
+ "0": "anger",
59
+ "1": "disgust",
60
+ "2": "fear",
61
+ "3": "happiness",
62
+ "4": "sadness"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 4096,
66
+ "label2id": {
67
+ "anger": 0,
68
+ "disgust": 1,
69
+ "fear": 2,
70
+ "happiness": 3,
71
+ "sadness": 4
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.1,
75
+ "mask_channel_length": 10,
76
+ "mask_channel_min_space": 1,
77
+ "mask_channel_other": 0.0,
78
+ "mask_channel_prob": 0.0,
79
+ "mask_channel_selection": "static",
80
+ "mask_feature_length": 10,
81
+ "mask_feature_prob": 0.0,
82
+ "mask_time_length": 10,
83
+ "mask_time_min_space": 1,
84
+ "mask_time_other": 0.0,
85
+ "mask_time_prob": 0.05,
86
+ "mask_time_selection": "static",
87
+ "model_type": "wav2vec2",
88
+ "num_attention_heads": 16,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 24,
95
+ "num_negatives": 100,
96
+ "pad_token_id": 54,
97
+ "pooling_mode": "mean",
98
+ "problem_type": "single_label_classification",
99
+ "proj_codevector_dim": 256,
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.11.0.dev0",
102
+ "use_weighted_layer_sum": false,
103
+ "vocab_size": 55
104
+ }
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb33a3dd9524c47e469015d6cee59a0c088df175e696c33d38db258b341ba92
3
+ size 2498486793
checkpoint-300/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-300/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fca4831614ee2cf814899e61045641219ed7f3f7dc12e95c1ed1f99ccecd501
3
+ size 1266137389
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808fe6cf963b70701bf53d4a6d57bd08f9f06b8a178de5d2eee505c75d958e3f
3
+ size 13611
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8617a797960edeb826fbb065dec017c8ed8e72ea3b4d9fb60cdb43863d8083
3
+ size 623
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.991735537190083,
5
+ "global_step": 300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.66,
12
+ "learning_rate": 6.666666666666667e-05,
13
+ "loss": 1.3311,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 1.66,
18
+ "eval_accuracy": 0.6033057570457458,
19
+ "eval_loss": 1.0739655494689941,
20
+ "eval_runtime": 74.6016,
21
+ "eval_samples_per_second": 1.622,
22
+ "eval_steps_per_second": 0.416,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 3.33,
27
+ "learning_rate": 3.3333333333333335e-05,
28
+ "loss": 0.6235,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 3.33,
33
+ "eval_accuracy": 0.8512396812438965,
34
+ "eval_loss": 0.47899967432022095,
35
+ "eval_runtime": 71.6672,
36
+ "eval_samples_per_second": 1.688,
37
+ "eval_steps_per_second": 0.433,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 4.99,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.2154,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 4.99,
48
+ "eval_accuracy": 0.9008264541625977,
49
+ "eval_loss": 0.3769935369491577,
50
+ "eval_runtime": 73.3118,
51
+ "eval_samples_per_second": 1.65,
52
+ "eval_steps_per_second": 0.423,
53
+ "step": 300
54
+ }
55
+ ],
56
+ "max_steps": 300,
57
+ "num_train_epochs": 5,
58
+ "total_flos": 4.279570856908188e+17,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfa74cde1a819557f67b8d79ebbc972342f238ccab6b70489c4baf413332bb7
3
+ size 2799
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lighteternal/wav2vec2-large-xlsr-53-greek",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForSpeechClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 256,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": true,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.0,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "finetuning_task": "wav2vec2_clf",
53
+ "gradient_checkpointing": true,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.1,
56
+ "hidden_size": 1024,
57
+ "id2label": {
58
+ "0": "anger",
59
+ "1": "disgust",
60
+ "2": "fear",
61
+ "3": "happiness",
62
+ "4": "sadness"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 4096,
66
+ "label2id": {
67
+ "anger": 0,
68
+ "disgust": 1,
69
+ "fear": 2,
70
+ "happiness": 3,
71
+ "sadness": 4
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.1,
75
+ "mask_channel_length": 10,
76
+ "mask_channel_min_space": 1,
77
+ "mask_channel_other": 0.0,
78
+ "mask_channel_prob": 0.0,
79
+ "mask_channel_selection": "static",
80
+ "mask_feature_length": 10,
81
+ "mask_feature_prob": 0.0,
82
+ "mask_time_length": 10,
83
+ "mask_time_min_space": 1,
84
+ "mask_time_other": 0.0,
85
+ "mask_time_prob": 0.05,
86
+ "mask_time_selection": "static",
87
+ "model_type": "wav2vec2",
88
+ "num_attention_heads": 16,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 24,
95
+ "num_negatives": 100,
96
+ "pad_token_id": 54,
97
+ "pooling_mode": "mean",
98
+ "problem_type": "single_label_classification",
99
+ "proj_codevector_dim": 256,
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.11.0.dev0",
102
+ "use_weighted_layer_sum": false,
103
+ "vocab_size": 55
104
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.99,
3
+ "eval_accuracy": 0.9008264541625977,
4
+ "eval_loss": 0.3769935369491577,
5
+ "eval_runtime": 72.4575,
6
+ "eval_samples": 121,
7
+ "eval_samples_per_second": 1.67,
8
+ "eval_steps_per_second": 0.428
9
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fca4831614ee2cf814899e61045641219ed7f3f7dc12e95c1ed1f99ccecd501
3
+ size 1266137389
runs/Sep18_15-19-28_bagus-IStDXi-M049/1631945991.8919263/events.out.tfevents.1631945991.bagus-IStDXi-M049.210250.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2960c3f848f57903dbc532365e95381d98a2a3767e8b21641fce2339e720e768
3
+ size 4364
runs/Sep18_15-19-28_bagus-IStDXi-M049/events.out.tfevents.1631945991.bagus-IStDXi-M049.210250.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec6bd2aca8fa6165c9d620f9030c5668aaaa98941610650be047473968e210a
3
+ size 6394
runs/Sep18_15-19-28_bagus-IStDXi-M049/events.out.tfevents.1631950866.bagus-IStDXi-M049.210250.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed79f1cfe99f827a0a4163f011c0aa880285f06c1a2e6de96d4f1c80568b3611
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.99,
3
+ "train_loss": 0.7233316548665365,
4
+ "train_runtime": 4793.1545,
5
+ "train_samples": 483,
6
+ "train_samples_per_second": 0.504,
7
+ "train_steps_per_second": 0.063
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.991735537190083,
5
+ "global_step": 300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.66,
12
+ "learning_rate": 6.666666666666667e-05,
13
+ "loss": 1.3311,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 1.66,
18
+ "eval_accuracy": 0.6033057570457458,
19
+ "eval_loss": 1.0739655494689941,
20
+ "eval_runtime": 74.6016,
21
+ "eval_samples_per_second": 1.622,
22
+ "eval_steps_per_second": 0.416,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 3.33,
27
+ "learning_rate": 3.3333333333333335e-05,
28
+ "loss": 0.6235,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 3.33,
33
+ "eval_accuracy": 0.8512396812438965,
34
+ "eval_loss": 0.47899967432022095,
35
+ "eval_runtime": 71.6672,
36
+ "eval_samples_per_second": 1.688,
37
+ "eval_steps_per_second": 0.433,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 4.99,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.2154,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 4.99,
48
+ "eval_accuracy": 0.9008264541625977,
49
+ "eval_loss": 0.3769935369491577,
50
+ "eval_runtime": 73.3118,
51
+ "eval_samples_per_second": 1.65,
52
+ "eval_steps_per_second": 0.423,
53
+ "step": 300
54
+ },
55
+ {
56
+ "epoch": 4.99,
57
+ "step": 300,
58
+ "total_flos": 4.279570856908188e+17,
59
+ "train_loss": 0.7233316548665365,
60
+ "train_runtime": 4793.1545,
61
+ "train_samples_per_second": 0.504,
62
+ "train_steps_per_second": 0.063
63
+ }
64
+ ],
65
+ "max_steps": 300,
66
+ "num_train_epochs": 5,
67
+ "total_flos": 4.279570856908188e+17,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfa74cde1a819557f67b8d79ebbc972342f238ccab6b70489c4baf413332bb7
3
+ size 2799